The spread of misinformation through synthetically generated yet realistic images and videos has become a significant problem, calling for robust manipulation detection methods. Despite the predominant effort of detecting face manipulation in still images, less attention has been paid to the identification of tampered faces in videos by taking advantage of the temporal information present in the stream. Recurrent convolutional models are a class of deep learning models which have proven effective at exploiting the temporal information from image streams across domains. We thereby distill the best strategy for combining variations in these models along with domain specific face preprocessing techniques through extensive experimentation to obtain state-of-the-art performance on publicly available video-based facial manipulation benchmarks. Specifically, we attempt to detect Deepfake, Face2Face and FaceSwap tampered faces in video streams. Evaluation is performed on the recently introduced FaceForensics++ dataset, improving the previous state-of-the-art by up to 4.55% in accuracy.
http://arxiv.org/abs/1905.00582
The majority of current studies on autonomous vehicle control via deep reinforcement learning (DRL) utilize point-mass kinematic models, neglecting vehicle dynamics which includes acceleration delay and acceleration command dynamics. The acceleration delay, which results from sensing and actuation delays, results in delayed execution of the control inputs. The acceleration command dynamics dictates that the actual vehicle acceleration does not rise up to the desired command acceleration instantaneously due to friction and road grades. In this work, we investigate the feasibility of applying DRL controllers trained using vehicle kinematic models to more realistic driving control with vehicle dynamics. We consider a particular longitudinal car-following control, i.e., Adaptive Cruise Control, problem solved via DRL using a point-mass kinematic model. When such a controller is applied to car following with vehicle dynamics, we observe significantly degraded car-following performance. Therefore, we redesign the DRL framework to accommodate the acceleration delay and acceleration command dynamics by adding the delayed control inputs and the actual vehicle acceleration to the reinforcement learning environment state. The training results show that the redesigned DRL controller results in near-optimal control performance of car following with vehicle dynamics considered when compared with dynamic programming solutions.
http://arxiv.org/abs/1905.08314
Multispectral person detection aims at automatically localizing humans in images that consist of multiple spectral bands. Usually, the visual-optical (VIS) and the thermal infrared (IR) spectra are combined to achieve higher robustness for person detection especially in insufficiently illuminated scenes. This paper focuses on analyzing existing detection approaches for their generalization ability. Generalization is a key feature for machine learning based detection algorithms that are supposed to perform well across different datasets. Inspired by recent literature regarding person detection in the VIS spectrum, we perform a cross-validation study to empirically determine the most promising dataset to train a well-generalizing detector. Therefore, we pick one reference Deep Convolutional Neural Network (DCNN) architecture and three different multispectral datasets. The Region Proposal Network (RPN) originally introduced for object detection within the popular Faster R-CNN is chosen as a reference DCNN. The reason is that a stand-alone RPN is able to serve as a competitive detector for two-class problems such as person detection. Furthermore, current state-of-the-art approaches initially apply an RPN followed by individual classifiers. The three considered datasets are the KAIST Multispectral Pedestrian Benchmark including recently published improved annotations for training and testing, the Tokyo Multi-spectral Semantic Segmentation dataset, and the OSU Color-Thermal dataset including recently released annotations. The experimental results show that the KAIST Multispectral Pedestrian Benchmark with its improved annotations provides the best basis to train a DCNN with good generalization ability compared to the other two multispectral datasets. On average, this detection model achieves a log-average Miss Rate (MR) of 29.74 % evaluated on the reasonable test subsets of the three datasets.
http://arxiv.org/abs/1905.02758
Unconstrained video-based face recognition is a challenging problem due to significant within-video variations caused by pose, occlusion and blur. To tackle this problem, an effective idea is to propagate the identity from high-quality faces to low-quality ones through contextual connections, which are constructed based on context such as body appearance. However, previous methods have often propagated erroneous information due to lack of uncertainty modeling of the noisy contextual connections. In this paper, we propose the Uncertainty-Gated Graph (UGG), which conducts graph-based identity propagation between tracklets, which are represented by nodes in a graph. UGG explicitly models the uncertainty of the contextual connections by adaptively updating the weights of the edge gates according to the identity distributions of the nodes during inference. UGG is a generic graphical model that can be applied at only inference time or with end-to-end training. We demonstrate the effectiveness of UGG with state-of-the-art results in the recently released challenging Cast Search in Movies and IARPA Janus Surveillance Video Benchmark dataset.
http://arxiv.org/abs/1905.02756
In this work, we propose a novel method for training neural networks to perform single-document extractive summarization without heuristically-generated extractive labels. We call our approach BanditSum as it treats extractive summarization as a contextual bandit (CB) problem, where the model receives a document to summarize (the context), and chooses a sequence of sentences to include in the summary (the action). A policy gradient reinforcement learning algorithm is used to train the model to select sequences of sentences that maximize ROUGE score. We perform a series of experiments demonstrating that BanditSum is able to achieve ROUGE scores that are better than or comparable to the state-of-the-art for extractive summarization, and converges using significantly fewer update steps than competing approaches. In addition, we show empirically that BanditSum performs significantly better than competing approaches when good summary sentences appear late in the source document.
http://arxiv.org/abs/1809.09672
Convolutional Neural Network (CNN) is achieving remarkable progress in various computer vision tasks. In the past few years, the remote sensing community has observed Deep Neural Network (DNN) finally taking off in several challenging fields. In this study, we propose a DNN to generate a predefined High Resolution (HR) synthetic spectral band using an ensemble of concurrent Low Resolution (LR) bands and existing HR bands. Of particular interest, the proposed network, namely DeepSWIR, synthesizes Short-Wave InfraRed (SWIR) band at 5m Ground Sampling Distance (GSD) using Green (G), Red (R) and Near InfraRed (NIR) bands at both 24m and 5m GSD, and SWIR band at 24m GSD. To our knowledge, the highest spatial resolution of commercially deliverable SWIR band is at 7.5m GSD. Also, we propose a Gaussian feathering based image stitching approach in light of processing large satellite imagery. To experimentally validate the synthesized HR SWIR band, we critically analyse the qualitative and quantitative results produced by DeepSWIR using state-of-the-art evaluation metrics. Further, we convert the synthesized DN values to Top Of Atmosphere (TOA) reflectance and compare with the corresponding band of Sentinel-2B. Finally, we show one real world application of the synthesized band by using it to map wetland resources over our region of interest.
http://arxiv.org/abs/1905.02749
An accurate depth map of the environment is critical to the safe operation of autonomous robots and vehicles. Currently, either light detection and ranging (LIDAR) or stereo matching algorithms are used to acquire such depth information. However, a high-resolution LIDAR is expensive and produces sparse depth map at large range; stereo matching algorithms are able to generate denser depth maps but are typically less accurate than LIDAR at long range. This paper combines these approaches together to generate high-quality dense depth maps. Unlike previous approaches that are trained using ground-truth labels, the proposed model adopts a self-supervised training process. Experiments show that the proposed method is able to generate high-quality dense depth maps and performs robustly even with low-resolution inputs. This shows the potential to reduce the cost by using LIDARs with lower resolution in concert with stereo systems while maintaining high resolution.
http://arxiv.org/abs/1905.02744
Video restoration tasks, including super-resolution, deblurring, etc, are drawing increasing attention in the computer vision community. A challenging benchmark named REDS is released in the NTIRE19 Challenge. This new benchmark challenges existing methods from two aspects: (1) how to align multiple frames given large motions, and (2) how to effectively fuse different frames with diverse motion and blur. In this work, we propose a novel Video Restoration framework with Enhanced Deformable networks, termed EDVR, to address these challenges. First, to handle large motions, we devise a Pyramid, Cascading and Deformable (PCD) alignment module, in which frame alignment is done at the feature level using deformable convolutions in a coarse-to-fine manner. Second, we propose a Temporal and Spatial Attention (TSA) fusion module, in which attention is applied both temporally and spatially, so as to emphasize important features for subsequent restoration. Thanks to these modules, our EDVR wins the champions and outperforms the second place by a large margin in all four tracks in the NTIRE19 video restoration and enhancement challenges. EDVR also demonstrates superior performance to state-of-the-art published methods on video super-resolution and deblurring. The code is available at this https URL.
https://arxiv.org/abs/1905.02716
The Alt-Right is a neo-fascist white supremacist movement that is involved in violent extremism and shows signs of engagement in extensive disinformation campaigns. Using social media data mining, this study develops a deeper understanding of such targeted disinformation campaigns and the ways they spread. It also adds to the available literature on the endogenous and exogenous influences within the US far right, as well as motivating factors that drive disinformation campaigns, such as geopolitical strategy. This study is to be taken as a preliminary analysis to indicate future methods and follow-on research that will help develop an integrated approach to understanding the strategies and associations of the modern fascist movement.
https://arxiv.org/abs/1905.02712
Occlusion removal is an interesting application of image enhancement, for which, existing work suggests manually-annotated or domain-specific occlusion removal. No work tries to address automatic occlusion detection and removal as a context-aware generic problem. In this paper, we present a novel methodology to identify objects that do not relate to the image context as occlusions and remove them, reconstructing the space occupied coherently. The proposed system detects occlusions by considering the relation between foreground and background object classes represented as vector embeddings, and removes them through inpainting. We test our system on COCO-Stuff dataset and conduct a user study to establish a baseline in context-aware automatic occlusion removal.
https://arxiv.org/abs/1905.02710
We propose a deep inverse rendering framework for indoor scenes. From a single RGB image of an arbitrary indoor scene, we create a complete scene reconstruction, estimating shape, spatially-varying lighting, and spatially-varying, non-Lambertian surface reflectance. To train this network, we augment the SUNCG indoor scene dataset with real-world materials and render them with a fast, high-quality, physically-based GPU renderer to create a large-scale, photorealistic indoor dataset. Our inverse rendering network incorporates physical insights – including a spatially-varying spherical Gaussian lighting representation, a differentiable rendering layer to model scene appearance, a cascade structure to iteratively refine the predictions and a bilateral solver for refinement – allowing us to jointly reason about shape, lighting, and reflectance. Experiments show that our framework outperforms previous methods for estimating individual scene components, which also enables various novel applications for augmented reality, such as photorealistic object insertion and material editing. Code and data will be made publicly available.
http://arxiv.org/abs/1905.02722
We present a learning based approach for multi-view stereopsis (MVS). While current deep MVS methods achieve impressive results, they crucially rely on ground-truth 3D training data, and acquisition of such precise 3D geometry for supervision is a major hurdle. Our framework instead leverages photometric consistency between multiple views as supervisory signal for learning depth prediction in a wide baseline MVS setup. However, naively applying photo consistency constraints is undesirable due to occlusion and lighting changes across views. To overcome this, we propose a robust loss formulation that: a) enforces first order consistency and b) for each point, selectively enforces consistency with some views, thus implicitly handling occlusions. We demonstrate our ability to learn MVS without 3D supervision using a real dataset, and show that each component of our proposed robust loss results in a significant improvement. We qualitatively observe that our reconstructions are often more complete than the acquired ground truth, further showing the merits of this approach. Lastly, our learned model generalizes to novel settings, and our approach allows adaptation of existing CNNs to datasets without ground-truth 3D by unsupervised finetuning. Project webpage: this https URL
https://arxiv.org/abs/1905.02706
Although deep reinforcement learning has advanced significantly over the past several years, sample efficiency remains a major challenge. Careful choice of input representations can help improve efficiency depending on the structure present in the problem. In this work, we present an attention-based method to project inputs into an efficient representation space that is invariant under changes to input ordering. We show that our proposed representation results in a search space that is a factor of m! smaller for inputs of m objects. Our experiments demonstrate improvements in sample efficiency for policy gradient methods on a variety of tasks. We show that our representation allows us to solve problems that are otherwise intractable when using naive approaches.
https://arxiv.org/abs/1905.02698
Humans make decisions and act alongside other humans to pursue both short-term and long-term goals. As a result of ongoing progress in areas such as computing science and automation, humans now also interact with non-human agents of varying complexity as part of their day-to-day activities; substantial work is being done to integrate increasingly intelligent machine agents into human work and play. With increases in the cognitive, sensory, and motor capacity of these agents, intelligent machinery for human assistance can now reasonably be considered to engage in joint action with humans—i.e., two or more agents adapting their behaviour and their understanding of each other so as to progress in shared objectives or goals. The mechanisms, conditions, and opportunities for skillful joint action in human-machine partnerships is of great interest to multiple communities. Despite this, human-machine joint action is as yet under-explored, especially in cases where a human and an intelligent machine interact in a persistent way during the course of real-time, daily-life experience. In this work, we contribute a virtual reality environment wherein a human and an agent can adapt their predictions, their actions, and their communication so as to pursue a simple foraging task. In a case study with a single participant, we provide an example of human-agent coordination and decision-making involving prediction learning on the part of the human and the machine agent, and control learning on the part of the machine agent wherein audio communication signals are used to cue its human partner in service of acquiring shared reward. These comparisons suggest the utility of studying human-machine coordination in a virtual reality environment, and identify further research that will expand our understanding of persistent human-machine joint action.
https://arxiv.org/abs/1905.02691
Autonomy is fundamental for artificial agents acting in complex real-world scenarios. The acquisition of many different skills is pivotal to foster versatile autonomous behaviour and thus a main objective for robotics and machine learning. Intrinsic motivations have proven to properly generate a task-agnostic signal to drive the autonomous acquisition of multiple policies in settings requiring the learning of multiple tasks. However, in real world scenarios tasks may be interdependent so that some of them may constitute the precondition for learning other ones. Despite different strategies have been used to tackle the acquisition of interdependent/hierarchical tasks, fully autonomous open-ended learning in these scenarios is still an open question. Building on previous research within the framework of intrinsically-motivated open-ended learning, we propose an architecture for robot control that tackles this problem from the point of view of decision making, i.e. treating the selection of tasks as a Markov Decision Process where the system selects the policies to be trained in order to maximise its competence over all the tasks. The system is then tested with a humanoid robot solving interdependent multiple reaching tasks.
http://arxiv.org/abs/1905.02690
Automatic segmentation of fine-grained brain structures remains a challenging task. Current segmentation methods mainly utilize 2D and 3D deep neural networks. The 2D networks take image slices as input to produce coarse segmentation in less processing time, whereas the 3D networks take the whole image volumes to generated fine-detailed segmentation with more computational burden. In order to obtain accurate fine-grained segmentation efficiently, in this paper, we propose an end-to-end Feature-Fused Context-Encoding Network for brain structure segmentation from MR (magnetic resonance) images. Our model is implemented based on a 2D convolutional backbone, which integrates a 2D encoding module to acquire planar image features and a spatial encoding module to extract spatial context information. A global context encoding module is further introduced to capture global context semantics from the fused 2D encoding and spatial features. The proposed network aims to fully leverage the global anatomical prior knowledge learned from context semantics, which is represented by a structure-aware attention factor to recalibrate the outputs of the network. In this way, the network is guaranteed to be aware of the class-dependent feature maps to facilitate the segmentation. We evaluate our model on 2012 Brain Multi-Atlas Labelling Challenge dataset for 134 fine-grained structure segmentation. Besides, we validate our network on 27 coarse structure segmentation tasks. Experimental results have demonstrated that our model can achieve improved performance compared with the state-of-the-art approaches.
https://arxiv.org/abs/1905.02686
Bayesian optimization has demonstrated impressive success in finding the optimum location $x^{}$ and value $f^{}=f(x^{})=\max_{x\in\mathcal{X}}f(x)$ of the black-box function $f$. In some applications, however, the optimum value is known in advance and the goal is to find the corresponding optimum location. Existing work in Bayesian optimization (BO) has not effectively exploited the knowledge of $f^{}$ for optimization. In this paper, we consider a new setting in BO in which the knowledge of the optimum value is available. Our goal is to exploit the knowledge about $f^{}$ to search for the location $x^{}$ efficiently. To achieve this goal, we first transform the Gaussian process surrogate using the information about the optimum value. Then, we propose two acquisition functions, called confidence bound minimization and expected regret minimization, which exploit the knowledge about the optimum value to identify the optimum location efficiently. We show that our approaches work both intuitively and quantitatively achieve better performance against standard BO methods. We demonstrate real applications in tuning a deep reinforcement learning algorithm on the CartPole problem and XGBoost on Skin Segmentation dataset in which the optimum values are publicly available.
https://arxiv.org/abs/1905.02685
This work evaluates the efficacy of adversarial robustness under transfer from CIFAR 100 to CIFAR 10. This allows us to identify transfer learning strategies under which adversarial defences are successfully retained, in addition to revealing potential vulnerabilities. We study the extent to which features crafted by fast gradient sign methods (FGSM) and their iterative alternative (PGD) can preserve their defence properties against black and white-box attacks under three different transfer learning strategies. We find that using PGD examples during training leads to more general robustness that is easier to transfer. Furthermore, under successful transfer, it achieves 5.2% more accuracy against white-box PGD attacks than the considered baselines. In this paper, we study the effects of using robust optimisation in the source and target networks. Our empirical evaluation sheds light on how well such mechanisms generalise while achieving comparable results to non-transferred defences.
https://arxiv.org/abs/1905.02675
Episodic memory plays an important role in the behavior of animals and humans. It allows the accumulation of information about current state of the environment in a task-agnostic way. This episodic representation can be later accessed by down-stream tasks in order to make their execution more efficient. In this work, we introduce the neural architecture with shared episodic memory (SEM) for learning and the sequential execution of multiple tasks. We explicitly split the encoding of episodic memory and task-specific memory into separate recurrent sub-networks. An agent augmented with SEM was able to effectively reuse episodic knowledge collected during other tasks to improve its policy on a current task in the Taxi problem. Repeated use of episodic representation in continual learning experiments facilitated acquisition of novel skills in the same environment.
https://arxiv.org/abs/1905.02662
We present a generalization of the person-image generation task, in which a human image is generated conditioned on a target pose and a set X of source appearance images. In this way, we can exploit multiple, possibly complementary images of the same person which are usually available at training and at testing time. The solution we propose is mainly based on a local attention mechanism which selects relevant information from different source image regions, avoiding the necessity to build specific generators for each specific cardinality of X. The empirical evaluation of our method shows the practical interest of addressing the person-image generation problem in a multi-source setting.
https://arxiv.org/abs/1905.02655
We present a novel high frequency residual learning framework, which leads to a highly efficient multi-scale network (MSNet) architecture for mobile and embedded vision problems. The architecture utilizes two networks: a low resolution network to efficiently approximate low frequency components and a high resolution network to learn high frequency residuals by reusing the upsampled low resolution features. With a classifier calibration module, MSNet can dynamically allocate computation resources during inference to achieve a better speed and accuracy trade-off. We evaluate our methods on the challenging ImageNet-1k dataset and observe consistent improvements over different base networks. On ResNet-18 and MobileNet with alpha=1.0, MSNet gains 1.5% accuracy over both architectures without increasing computations. On the more efficient MobileNet with alpha=0.25, our method gains 3.8% accuracy with the same amount of computations.
https://arxiv.org/abs/1905.02649
In this paper, we present a framework for performing collaborative localization for groups of micro aerial vehicles (MAV) that use vision based sensing. The vehicles are each assumed to be equipped with a forward-facing monocular camera, and to be capable of communicating with each other. This collaborative localization approach is developed as a decentralized algorithm and built in a distributed fashion where individual and relative pose estimation techniques are combined for the group to localize against surrounding environments. The MAVs initially detect and match salient features between each other to create a sparse reconstruction of the observed environment, which acts as a global map. Once a map is available, each MAV performs feature detection and tracking with a robust outlier rejection process to estimate its own pose in 6 degrees of freedom. Occasionally, one or more MAVs can be tasked to compute poses for another MAV through relative measurements, which is achieved through multiple view geometry concepts. These relative measurements are then fused with individual measurements in a consistent fashion. We present the results of the algorithm on image data from MAV flights both in simulation and real life, and discuss the advantages of collaborative localization in improving pose estimation accuracy.
http://arxiv.org/abs/1905.02648
Domain-specific community question answering is becoming an integral part of professions. Finding related questions and answers in these communities can significantly improve the effectiveness and efficiency of information seeking. Stack Overflow is one of the most popular communities that is being used by millions of programmers. In this paper, we analyze the problem of predicting knowledge unit (question thread) relatedness in Stack Overflow. In particular, we formulate the question relatedness task as a multi-class classification problem with four degrees of relatedness. We present a large-scale dataset with more than 300K pairs. To the best of our knowledge, this dataset is the largest domain-specific dataset for Question-Question relatedness. We present the steps that we took to collect, clean, process, and assure the quality of the dataset. The proposed dataset Stack Overflow is a useful resource to develop novel solutions, specifically data-hungry neural network models, for the prediction of relatedness in technical community question-answering forums. We adopt a neural network architecture and a traditional model for this task that effectively utilize information from different parts of knowledge units to compute the relatedness between them. These models can be used to benchmark novel models, as they perform well in our task and in a closely similar task.
https://arxiv.org/abs/1905.01966
For researching effects of gamification in foreign language learning for children in the “Say It Again, Kid!” project we developed a feedback paradigm that can drive gameplay in pronunciation learning games. We describe our scoring system based on the difference between a reference phone sequence and the output of a multilingual CTC phoneme recogniser. We present a white-box scoring model of mapped weighted Levenshtein edit distance between reference and error with error weights for articulatory differences computed from a training set of scored utterances. The system can produce a human-readable list of each detected mispronunciation’s contribution to the utterance score. We compare our scoring method to established black box methods.
https://arxiv.org/abs/1905.02639
Complex social systems are composed of interconnected individuals whose interactions result in group behaviors. Optimal control of a real-world complex system has many applications, including road traffic management, epidemic prevention, and information dissemination. However, such real-world complex system control is difficult to achieve because of high-dimensional and non-linear system dynamics, and the exploding state and action spaces for the decision maker. Prior methods can be divided into two categories: simulation-based and analytical approaches. Existing simulation approaches have high-variance in Monte Carlo integration, and the analytical approaches suffer from modeling inaccuracy. We adopted simulation modeling in specifying the complex dynamics of a complex system, and developed analytical solutions for searching optimal strategies in a complex network with high-dimensional state-action space. To capture the complex system dynamics, we formulate the complex social network decision making problem as a discrete event decision process. To address the curse of dimensionality and search in high-dimensional state action spaces in complex systems, we reduce control of a complex system to variational inference and parameter learning, introduce Bethe entropy approximation, and develop an expectation propagation algorithm. Our proposed algorithm leads to higher system expected rewards, faster convergence, and lower variance of value function in a real-world transportation scenario than state-of-the-art analytical and sampling approaches.
https://arxiv.org/abs/1905.02606
Typically, deep learning architectures are handcrafted for their respective learning problem. As an alternative, neural architecture search (NAS) has been proposed where the architecture’s structure is learned in an additional optimization step. For the medical imaging domain, this approach is very promising as there are diverse problems and imaging modalities that require architecture design. However, NAS is very time-consuming and medical learning problems often involve high-dimensional data with high computational requirements. We propose an efficient approach for NAS in the context of medical, image-based deep learning problems by searching for architectures on low-dimensional data which are subsequently transferred to high-dimensional data. For OCT-based layer segmentation, we demonstrate that a search on 1D data reduces search time by 87.5% compared to a search on 2D data while the final 2D models achieve similar performance.
https://arxiv.org/abs/1905.02590
Object detection has been vigorously studied for years but fast accurate detection for real-world scenes remains a very challenging problem. Overcoming drawbacks of single-stage detectors, we take aim at precisely detecting objects for static and temporal scenes in real time. Firstly, as a dual refinement mechanism, a novel anchor-offset detection including an anchor refinement, a feature offset refinement, and a deformable detection head is designed for two-step regression and capture of accurate detection features. Based on the anchor-offset detection, a dual refinement network (DRN) is developed for high-performance static detection, where a multi-deformable head is further designed to leverage contextual information for describing objects. As for temporal detection in real-world scenes, temporal refinement networks (TRN) and temporal dual refinement networks (TDRN) are developed by propagating the refinement information across time, where we also propose a loose refinement strategy to match object motion with the previous refinement. Our proposed methods are evaluated on PASCAL VOC, COCO, and ImageNet VID datasets. Extensive comparison on static and temporal detection verify the superiority of DRN, TRN, and TDRN. Consequently, our developed approaches run in a fairly fast speed, and in the meantime achieve a significantly enhanced detection accuracy, i.e., a mAP of 82.8% on VOC 2007, 80.6% on VOC 2012, 69.4% on VID 2017, and an AP of 34.3% on COCO. Ultimately, producing encouraging results, our methods are applied to underwater object grasping with an autonomous system. Codes are publicly available at https://github.com/SeanChenxy/TDRN.
http://arxiv.org/abs/1807.08638
In recent years, descriptive evaluation has been introduced as a new model for educational evaluation of Iranian students. The current descriptive evaluation method is based on four-valued logic. Assessing all students with only four values is led to a lack of relative justice and the creation of unrealistic equality. Also, the complexity of the evaluation process in the current method increases teacher errors likelihood. As a suitable solution, in this paper, a fuzzy descriptive evaluation system has been proposed. The proposed method is based on fuzzy logic, which is an infinite-valued logic and it can perform approximate reasoning on natural language propositions. By the proposed fuzzy system, student assessment is performed over the school year with infinite values instead of four values. But to eliminate the diversity of assigned values to students, at the end of the school year, the calculated values for each student will be rounded to the nearest value of the four standard values of the current descriptive evaluation system. It can be implemented easily in an appropriate smartphone app, which makes it much easier for the teachers to evaluate the evaluation process. In this paper, the evaluation process of the elementary third-grade mathematics course in Iran during the period from the beginning of the MEHR (The Seventh month of Iran) to the end of BAHMAN (The Eleventh Month of Iran) is examined by the proposed system. To evaluate the validity of this system, the proposed method has been simulated in MATLAB software.
https://arxiv.org/abs/1905.02549
Ocular pathology detection from fundus images presents an important challenge on health care. In fact, each pathology has different severity stages that may be deduced by verifying the existence of specific lesions. Each lesion is characterized by morphological features. Moreover, several lesions of different pathologies have similar features. We note that patient may be affected simultaneously by several pathologies. Consequently, the ocular pathology detection presents a multi-class classification with a complex resolution principle. Several detection methods of ocular pathologies from fundus images have been proposed. The methods based on deep learning are distinguished by higher performance detection, due to their capability to configure the network with respect to the detection objective. This work proposes a survey of ocular pathology detection methods based on deep learning. First, we study the existing methods either for lesion segmentation or pathology classification. Afterwards, we extract the principle steps of processing and we analyze the proposed neural network structures. Subsequently, we identify the hardware and software environment required to employ the deep learning architecture. Thereafter, we investigate about the experimentation principles involved to evaluate the methods and the databases used either for training and testing phases. The detection performance ratios and execution times are also reported and discussed.
https://arxiv.org/abs/1905.02544
Demosaicing, denoising and super-resolution (SR) are of practical importance in digital image processing and have been studied independently in the passed decades. Despite the recent improvement of learning-based image processing methods in image quality, there lacks enough analysis into their interactions and characteristics under a realistic setting of the mixture problem of demosaicing, denoising and SR. In existing solutions, these tasks are simply combined to obtain a high-resolution image from a low-resolution raw mosaic image, resulting in a performance drop of the final image quality. In this paper, we first rethink the mixture problem from a holistic perspective and then propose the Trinity Enhancement Network (TENet), a specially designed learning-based method for the mixture problem, which adopts a novel image processing pipeline order and a joint learning strategy. In order to obtain the correct color sampling for training, we also contribute a new dataset namely PixelShift200, which consists of high-quality full color sampled real-world images using the advanced pixel shift technique. Experiments demonstrate that our TENet is superior to existing solutions in both quantitative and qualitative perspective. Our experiments also show the necessity of the proposed PixelShift200 dataset.
https://arxiv.org/abs/1905.02538
Compared to the heavily studied surface drainage systems, the mountain ridge systems have been a subject of less attention even on the empirical level, despite the fact that their structure is richer. To reduce this deficiency, we analyze different mountain ranges by means of a network approach and grasp some essential features of the ridge branching structure. We also employ a fractal analysis as it is especially suitable for describing properties of rough objects and surfaces. As our approach differs from typical analyses that are carried out in geophysics, we believe that it can initialize a research direction that will allow to shed more light on the processes that are responsible for landscape formation and will contribute to the network theory by indicating a need for the construction of new models of the network growth as no existing model can properly describe the ridge formation. We also believe that certain features of our study can offer help in the cartographic generalization. Specifically, we study structure of the ridge networks based on the empirical elevation data collected by SRTM. We consider mountain ranges from different geological periods and geographical locations. For each mountain range, we construct a simple topographic network representation (the ridge junctions are nodes) and a ridge representation (the ridges are nodes and the junctions are edges) and calculate the parameters characterizing their topology. We observe that the topographic networks inherit the fractal structure of the mountain ranges but do not show any other complex features. In contrast, the ridge networks, while lacking the proper fractality, reveal the power-law degree distributions with the exponent $1.6\le \beta \le 1.7$. By taking into account the fact that the analyzed mountains differ in many properties, these values seem to be universal for the earthly mountainous terrain.
http://arxiv.org/abs/1804.03457
In this work we address supervised learning via lifted network formulations. Lifted networks are interesting because they allow training on massively parallel hardware and assign energy models to discriminatively trained neural networks. We demonstrate that training methods for lifted networks proposed in the literature have significant limitations, and therefore we propose to use a contrastive loss to train lifted networks. We show that this contrastive training approximates back-propagation in theory and in practice, and that it is superior to the regular training objective for lifted networks.
https://arxiv.org/abs/1905.02507
Despite recent progress in computer vision, finegrained interpretation of satellite images remains challenging because of a lack of labeled training data. To overcome this limitation, we construct a novel dataset called WikiSatNet by pairing georeferenced Wikipedia articles with satellite imagery of their corresponding locations. We then propose two strategies to learn representations of satellite images by predicting properties of the corresponding articles from the images. Leveraging this new multi-modal dataset, we can drastically reduce the quantity of human-annotated labels and time required for downstream tasks. On the recently released fMoW dataset, our pre-training strategies can boost the performance of a model pre-trained on ImageNet by up to 4:5% in F1 score.
https://arxiv.org/abs/1905.02506
Security Analysts that work in a `Security Operations Center’ (SoC) play a major role in ensuring the security of the organization. The amount of background knowledge they have about the evolving and new attacks makes a significant difference in their ability to detect attacks. Open source threat intelligence sources, like text descriptions about cyber-attacks, can be stored in a structured fashion in a cybersecurity knowledge graph. A cybersecurity knowledge graph can be paramount in aiding a security analyst to detect cyber threats because it stores a vast range of cyber threat information in the form of semantic triples which can be queried. A semantic triple contains two cybersecurity entities with a relationship between them. In this work, we propose a system to create semantic triples over cybersecurity text, using deep learning approaches to extract possible relationships. We use the set of semantic triples generated through our system to assert in a cybersecurity knowledge graph. Security Analysts can retrieve this data from the knowledge graph, and use this information to form a decision about a cyber-attack.
https://arxiv.org/abs/1905.02497
Keeping up with threat intelligence is a must for a security analyst today. There is a volume of information present in the wild' that affects an organization. We need to develop an artificial intelligence system that scours the intelligence sources, to keep the analyst updated about various threats that pose a risk to her organization. A security analyst who is better tapped in’ can be more effective.
In this paper we present, Cyber-All-Intel an artificial intelligence system to aid a security analyst. It is a system for knowledge extraction, representation and analytics in an end-to-end pipeline grounded in the cybersecurity informatics domain. It uses multiple knowledge representations like, vector spaces and knowledge graphs in a ‘VKG structure’ to store incoming intelligence. The system also uses neural network models to pro-actively improve its knowledge. We have also created a query engine and an alert system that can be used by an analyst to find actionable cybersecurity insights.
http://arxiv.org/abs/1905.02895
Hyperspectral image (HSI) classification, which aims to assign an accurate label for hyperspectral pixels, has drawn great interest in recent years. Although low rank representation (LRR) has been used to classify HSI, its ability to segment each class from the whole HSI data has not been exploited fully yet. LRR has a good capacity to capture the underlying lowdimensional subspaces embedded in original data. However, there are still two drawbacks for LRR. First, LRR does not consider the local geometric structure within data, which makes the local correlation among neighboring data easily ignored. Second, the representation obtained by solving LRR is not discriminative enough to separate different data. In this paper, a novel locality and structure regularized low rank representation (LSLRR) model is proposed for HSI classification. To overcome the above limitations, we present locality constraint criterion (LCC) and structure preserving strategy (SPS) to improve the classical LRR. Specifically, we introduce a new distance metric, which combines both spatial and spectral features, to explore the local similarity of pixels. Thus, the global and local structures of HSI data can be exploited sufficiently. Besides, we propose a structure constraint to make the representation have a near block-diagonal structure. This helps to determine the final classification labels directly. Extensive experiments have been conducted on three popular HSI datasets. And the experimental results demonstrate that the proposed LSLRR outperforms other state-of-the-art methods.
https://arxiv.org/abs/1905.02488
Current best local descriptors are learned on a large dataset of matching and non-matching keypoint pairs. However, data of this kind is not always available since detailed keypoint correspondences can be hard to establish. On the other hand, we can often obtain labels for pairs of keypoint bags. For example, keypoint bags extracted from two images of the same object under different views form a matching pair, and keypoint bags extracted from images of different objects form a non-matching pair. On average, matching pairs should contain more corresponding keypoints than non-matching pairs. We describe an end-to-end differentiable architecture that enables the learning of local keypoint descriptors from such weakly-labeled data. Additionally, we discuss how to improve the method by incorporating the procedure of mining hard negatives. We also show how can our approach be used to learn convolutional features from unlabeled video signals and 3D models. Our implementation is available at https://github.com/nenadmarkus/wlrn
http://arxiv.org/abs/1603.09095
Cosine-based softmax losses significantly improve the performance of deep face recognition networks. However, these losses always include sensitive hyper-parameters which can make training process unstable, and it is very tricky to set suitable hyper parameters for a specific dataset. This paper addresses this challenge by directly designing the gradients for adaptively training deep neural networks. We first investigate and unify previous cosine softmax losses by analyzing their gradients. This unified view inspires us to propose a novel gradient called P2SGrad (Probability-to-Similarity Gradient), which leverages a cosine similarity instead of classification probability to directly update the testing metrics for updating neural network parameters. P2SGrad is adaptive and hyper-parameter free, which makes the training process more efficient and faster. We evaluate our P2SGrad on three face recognition benchmarks, LFW, MegaFace, and IJB-C. The results show that P2SGrad is stable in training, robust to noise, and achieves state-of-the-art performance on all the three benchmarks.
https://arxiv.org/abs/1905.02479
Activation functions play a vital role in the training of Convolutional Neural Networks. For this reason, to develop efficient and performing functions is a crucial problem in the deep learning community. Key to these approaches is to permit a reliable parameter learning, avoiding vanishing gradient problems. The goal of this work is to propose an ensemble of Convolutional Neural Networks trained using several different activation functions. Moreover, a novel activation function is here proposed for the first time. Our aim is to improve the performance of Convolutional Neural Networks in small/medium size biomedical datasets. Our results clearly show that the proposed ensemble outperforms Convolutional Neural Networks trained with standard ReLU as activation function. The proposed ensemble outperforms with a p-value of 0.01 each tested stand-alone activation function; for reliable performance comparison we have tested our approach in more than 10 datasets, using two well-known Convolutional Neural Network: Vgg16 and ResNet50. MATLAB code used here will be available at this https URL.
https://arxiv.org/abs/1905.02473
For readability and possibly for disambiguation, appropriate word segmentation is recommended for written text. In this paper, we propose a real-time assistive technology that utilizes an automatic segmentation. The language investigated is Korean, a head-final language with various morpho-syllabic blocks as characters. The training scheme is fully neural network-based and straightforward. Besides, we show how the proposed system can be utilized in a web-based real-time revision for a user-generated text. With qualitative and quantitative comparison with widely used text processing toolkits, we show the reliability of the proposed system and how it fits with conversation-style and non-canonical texts. The demonstration is available online.
http://arxiv.org/abs/1810.13113
The correctness of deep neural networks is well-known to be vulnerable to small, ‘adversarial’ perturbations of their inputs. Although studying these attacks is valuable, they do not necessarily conform to any real-world threat model. This has led to interest in the generation of (and robustness to) unrestricted adversarial inputs, which are not constructed as small perturbations of correctly-classified ground-truth inputs. We introduce a novel algorithm to generate realistic unrestricted adversarial inputs, in the sense that they cannot reliably be distinguished from the training dataset by a human. This is achieved by modifying generative adversarial networks: a generator neural network is trained to construct examples that deceive a fixed target network (so they are adversarial) while also deceiving the usual co-training discriminator network (so they are realistic). Our approach is demonstrated by the generation of unrestricted adversarial inputs for a trained image classifier that is robust to perturbation-based attacks. We find that human judges are unable to identify which image out of ten was generated by our method about 50 percent of the time, providing evidence that they are moderately realistic.
https://arxiv.org/abs/1905.02463
Recently, image super-resolution has been widely studied and achieved significant progress by leveraging the power of deep convolutional neural networks. However, there has been limited advancement in video super-resolution (VSR) due to the complex temporal patterns in videos. In this paper, we investigate how to adapt state-of-the-art methods of image super-resolution for video super-resolution. The proposed adapting method is straightforward. The information among successive frames is well exploited, while the overhead on the original image super-resolution method is negligible. Furthermore, we propose a learning-based method to ensemble the outputs from multiple super-resolution models. Our methods show superior performance and rank second in the NTIRE2019 Video Super-Resolution Challenge Track 1.
https://arxiv.org/abs/1905.02462
Pre-training and fine-tuning, e.g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks. Inspired by the success of BERT, we propose MAsked Sequence to Sequence pre-training (MASS) for the encoder-decoder based language generation tasks. MASS adopts the encoder-decoder framework to reconstruct a sentence fragment given the remaining part of the sentence: its encoder takes a sentence with randomly masked fragment (several consecutive tokens) as input, and its decoder tries to predict this masked fragment. In this way, MASS can jointly train the encoder and decoder to develop the capability of representation extraction and language modeling. By further fine-tuning on a variety of zero/low-resource language generation tasks, including neural machine translation, text summarization and conversational response generation (3 tasks and totally 8 datasets), MASS achieves significant improvements over the baselines without pre-training or with other pre-training methods. Specially, we achieve the state-of-the-art accuracy (37.5 in terms of BLEU score) on the unsupervised English-French translation, even beating the early attention-based supervised model.
https://arxiv.org/abs/1905.02450
Now that everyone can easily record videos, the quantity of which is continuously increasing, research on methods for improved video retrieval is important in the contemporary world. In cases where target videos are to be identified within a large collection gathered by individuals, the appropriate information must be obtained to retrieve the correct video within a large number of similar items in the target database. The purpose of this research is to retrieve target videos in such cases by introducing an interaction, or a dialog, between the system and the user. We propose a system to retrieve videos by asking questions about the content of the videos and leveraging the user’s responses to the questions. Additionally, we confirmed the usefulness of the proposed system through experiments using the dataset called AVSD which includes videos and dialogs about the videos.
https://arxiv.org/abs/1905.02442
In this paper, we propose an intelligence approach based on fuzzy logic to modeling human intelligence in washing clothes. At first, an intelligent feedback loop is designed for perception-based sensing of dirt inspired by human color understanding. Then, when color stains leak out of some colored clothes the human probabilistic decision making is computationally modeled to detect this stain leakage and thus the problem of recognizing dirt from stain can be considered in the washing process. Finally, we discuss the fuzzy control of washing clothes and design and simulate a smart controller based on the fuzzy intelligence feedback loop.
https://arxiv.org/abs/1905.00607
In Multi-Agent Reinforcement Learning (MA-RL), independent cooperative learners must overcome a number of pathologies to learn optimal joint policies. Addressing one pathology often leaves approaches vulnerable towards others. For instance, hysteretic Q-learning addresses miscoordination while leaving agents vulnerable towards misleading stochastic rewards. Other methods, such as leniency, have proven more robust when dealing with multiple pathologies simultaneously. However, leniency has predominately been studied within the context of strategic form games (bimatrix games) and fully observable Markov games consisting of a small number of probabilistic state transitions. This raises the question of whether these findings scale to more complex domains. For this purpose we implement a temporally extend version of the Climb Game, within which agents must overcome multiple pathologies simultaneously, including relative overgeneralisation, stochasticity, the alter-exploration and moving target problems, while learning from a large observation space. We find that existing lenient and hysteretic approaches fail to consistently learn near optimal joint-policies in this environment. To address these pathologies we introduce Negative Update Intervals-DDQN (NUI-DDQN), a Deep MA-RL algorithm which discards episodes yielding cumulative rewards outside the range of expanding intervals. NUI-DDQN consistently gravitates towards optimal joint-policies in our environment, overcoming the outlined pathologies.
http://arxiv.org/abs/1809.05096
In this paper we present a novel interactive multimodal learning system, which facilitates search and exploration in large networks of social multimedia users. It allows the analyst to identify and select users of interest, and to find similar users in an interactive learning setting. Our approach is based on novel multimodal representations of users, words and concepts, which we simultaneously learn by deploying a general-purpose neural embedding model. We show these representations to be useful not only for categorizing users, but also for automatically generating user and community profiles. Inspired by traditional summarization approaches, we create the profiles by selecting diverse and representative content from all available modalities, i.e. the text, image and user modality. The usefulness of the approach is evaluated using artificial actors, which simulate user behavior in a relevance feedback scenario. Multiple experiments were conducted in order to evaluate the quality of our multimodal representations, to compare different embedding strategies, and to determine the importance of different modalities. We demonstrate the capabilities of the proposed approach on two different multimedia collections originating from the violent online extremism forum Stormfront and the microblogging platform Twitter, which are particularly interesting due to the high semantic level of the discussions they feature.
https://arxiv.org/abs/1905.02430
The extensive computational burden limits the usage of CNNs in mobile devices for dense estimation tasks. In this paper, we present a lightweight network to address this problem,namely LEDNet, which employs an asymmetric encoder-decoder architecture for the task of real-time semantic segmentation.More specifically, the encoder adopts a ResNet as backbone network, where two new operations, channel split and shuffle, are utilized in each residual block to greatly reduce computation cost while maintaining higher segmentation accuracy. On the other hand, an attention pyramid network (APN) is employed in the decoder to further lighten the entire network complexity. Our model has less than 1M parameters,and is able to run at over 71 FPS in a single GTX 1080Ti GPU. The comprehensive experiments demonstrate that our approach achieves state-of-the-art results in terms of speed and accuracy trade-off on CityScapes dataset.
https://arxiv.org/abs/1905.02423
The recent success of brain-inspired deep neural networks (DNNs) in solving complex, high-level visual tasks has led to rising expectations for their potential to match the human visual system. However, DNNs exhibit idiosyncrasies that suggest their visual representation and processing might be substantially different from human vision. One limitation of DNNs is that they are vulnerable to adversarial examples, input images on which subtle, carefully designed noises are added to fool a machine classifier. The robustness of the human visual system against adversarial examples is potentially of great importance as it could uncover a key mechanistic feature that machine vision is yet to incorporate. In this study, we compare the visual representations of white- and black-box adversarial examples in DNNs and humans by leveraging functional magnetic resonance imaging (fMRI). We find a small but significant difference in representation patterns for different (i.e. white- versus black- box) types of adversarial examples for both humans and DNNs. However, human performance on categorical judgment is not degraded by noise regardless of the type unlike DNN. These results suggest that adversarial examples may be differentially represented in the human visual system, but unable to affect the perceptual experience.
https://arxiv.org/abs/1905.02422
Recently average heart rate (HR) can be measured relatively accurately from human face videos based on non-contact remote photoplethysmography (rPPG). However in many healthcare applications, knowing only the average HR is not enough, and measured blood volume pulse signal and its heart rate variability (HRV) features are also important. We propose the first end-to-end rPPG signal recovering system (PhysNet) using deep spatio-temporal convolutional networks to measure both HR and HRV features. PhysNet extracts the spatial and temporal hidden features simultaneously from raw face sequences while outputs the corresponding rPPG signal directly. The temporal context information helps the network learn more robust features with less fluctuation. Our approach was tested on two datasets, and achieved superior performance of HR and HRV features comparing to the state-of-the-art methods.
https://arxiv.org/abs/1905.02419