Deep neural network models have recently draw lots of attention, as it consistently produce impressive results in many computer vision tasks such as image classification, object detection, etc. However, interpreting such model and show the reason why it performs quite well becomes a challenging question. In this paper, we propose a novel method to interpret the neural network models with attention mechanism. Inspired by the heatmap visualization, we analyze the relation between classification accuracy with the attention based heatmap. An improved attention based method is also included and illustrate that a better classifier can be interpreted by the attention based heatmap.
http://arxiv.org/abs/1901.10042
Existing visual reasoning datasets such as Visual Question Answering (VQA), often suffer from biases conditioned on the question, image or answer distributions. The recently proposed CLEVR dataset addresses these limitations and requires fine-grained reasoning but the dataset is synthetic and consists of similar objects and sentence structures across the dataset. In this paper, we introduce a new inference task, Visual Entailment (VE) - consisting of image-sentence pairs whereby a premise is defined by an image, rather than a natural language sentence as in traditional Textual Entailment tasks. The goal of a trained VE model is to predict whether the image semantically entails the text. To realize this task, we build a dataset SNLI-VE based on the Stanford Natural Language Inference corpus and Flickr30k dataset. We evaluate various existing VQA baselines and build a model called Explainable Visual Entailment (EVE) system to address the VE task. EVE achieves up to 71% accuracy and outperforms several other state-of-the-art VQA based models. Finally, we demonstrate the explainability of EVE through cross-modal attention visualizations. The SNLI-VE dataset is publicly available at https://github.com/ necla-ml/SNLI-VE.
http://arxiv.org/abs/1901.06706
The handwriting of an individual may vary substantially with factors such as mood, time, space, writing speed, writing medium and tool, writing topic, etc. It becomes challenging to perform automated writer verification/identification on a particular set of handwritten patterns (e.g., speedy handwriting) of a person, especially when the system is trained using a different set of writing patterns (e.g., normal speed) of that same person. However, it would be interesting to experimentally analyze if there exists any implicit characteristic of individuality which is insensitive to high intra-variable handwriting. In this paper, we study some handcrafted features and auto-derived features extracted from intra-variable writing. Here, we work on writer identification/verification from offline Bengali handwriting of high intra-variability. To this end, we use various models mainly based on handcrafted features with SVM (Support Vector Machine) and features auto-derived by the convolutional network. For experimentation, we have generated two handwritten databases from two different sets of 100 writers and enlarged the dataset by a data-augmentation technique. We have obtained some interesting results.
http://arxiv.org/abs/1708.03361
A comprehensive and systematic framework for easily extending and implementing the subset-based spatial-temporal digital image correlation (DIC) algorithm is presented. The framework decouples the three main factors (i.e. shape function, correlation criterion, and optimization algorithm) involved in algorithm implementation of DIC and represents different algorithms in a uniform form. One can freely choose and combine the three factors to meet his own need, or freely add more parameters to extract analytic results. Subpixel translation and a simulated image series with different velocity characters are analyzed using different algorithms based on the proposed framework, confirming the merit of noise suppression and velocity compatibility. An application of mitigating air disturbance due to heat haze using spatial-temporal DIC is given to demonstrate the applicability of the framework.
http://arxiv.org/abs/1812.04826
X-ray image based surgical tool navigation is fast and supplies accurate images of deep seated structures. Typically, recovering the 6 DOF rigid pose and deformation of tools with respect to the X-ray camera can be accurately achieved through intensity-based 2D/3D registration of 3D images or models to 2D X-rays. However, the capture range of image-based 2D/3D registration is inconveniently small suggesting that automatic and robust initialization strategies are of critical importance. This manuscript describes a first step towards leveraging semantic information of the imaged object to initialize 2D/3D registration within the capture range of image-based registration by performing concurrent segmentation and localization of dexterous surgical tools in X-ray images. We presented a learning-based strategy to simultaneously localize and segment dexterous surgical tools in X-ray images and demonstrate promising performance on synthetic and ex vivo data. We currently investigate methods to use semantic information extracted by the proposed network to reliably and robustly initialize image-based 2D/3D registration. While image-based 2D/3D registration has been an obvious focus of the CAI community, robust initialization thereof (albeit critical) has largely been neglected. This manuscript discusses learning-based retrieval of semantic information on imaged-objects as a stepping stone for such initialization and may therefore be of interest to the IPCAI community. Since results are still preliminary and only focus on localization, we target the Long Abstract category.
http://arxiv.org/abs/1901.06672
Supervised training of neural networks for classification is typically performed with a global loss function. The loss function provides a gradient for the output layer, and this gradient is back-propagated to hidden layers to dictate an update direction for the weights. An alternative approach is to train the network with layer-wise loss functions. In this paper we demonstrate, for the first time, that layer-wise training can approach the state-of-the-art on a variety of image datasets. We use single-layer sub-networks and two different supervised loss functions to generate local error signals for the hidden layers, and we show that the combination of these losses help with optimization in the context of local learning. Using local errors could be a step towards more biologically plausible deep learning because the global error does not have to be transported back to hidden layers. A completely backprop free variant outperforms previously reported results among methods aiming for higher biological plausibility. Code is available https://github.com/anokland/local-loss
http://arxiv.org/abs/1901.06656
As a long-standing problem in computer vision, face detection has attracted much attention in recent decades for its practical applications. With the availability of face detection benchmark WIDER FACE dataset, much of the progresses have been made by various algorithms in recent years. Among them, the Selective Refinement Network (SRN) face detector introduces the two-step classification and regression operations selectively into an anchor-based face detector to reduce false positives and improve location accuracy simultaneously. Moreover, it designs a receptive field enhancement block to provide more diverse receptive field. In this report, to further improve the performance of SRN, we exploit some existing techniques via extensive experiments, including new data augmentation strategy, improved backbone network, MS COCO pretraining, decoupled classification module, segmentation branch and Squeeze-and-Excitation block. Some of these techniques bring performance improvements, while few of them do not well adapt to our baseline. As a consequence, we present an improved SRN face detector by combining these useful techniques together and obtain the best performance on widely used face detection benchmark WIDER FACE dataset.
http://arxiv.org/abs/1901.06651
Community detection refers to the task of discovering groups of vertices sharing similar properties or functions so as to understand the network data. With the recent development of deep learning, graph representation learning techniques are also utilized for community detection. However, the communities can only be inferred by applying clustering algorithms based on learned vertex embeddings. These general cluster algorithms like K-means and Gaussian Mixture Model cannot output much overlapped communities, which have been proved to be very common in many real-world networks. In this paper, we propose CommunityGAN, a novel community detection framework that jointly solves overlapping community detection and graph representation learning. First, unlike the embedding of conventional graph representation learning algorithms where the vector entry values have no specific meanings, the embedding of CommunityGAN indicates the membership strength of vertices to communities. Second, a specifically designed Generative Adversarial Net (GAN) is adopted to optimize such embedding. Through the minimax competition between the motif-level generator and discriminator, both of them can alternatively and iteratively boost their performance and finally output a better community structure. Extensive experiments on synthetic data and real-world tasks demonstrate that CommunityGAN achieves substantial community detection performance gains over the state-of-the-art methods.
http://arxiv.org/abs/1901.06631
This paper presents Mixed Formal Learning, a new architecture that learns models based on formal mathematical representations of the domain of interest and exposes latent variables. The second element in the architecture learns a particular skill, typically by using traditional prediction or classification mechanisms. Our key findings include that this architecture: (1) Facilitates transparency by exposing key latent variables based on a learned mathematical model; (2) Enables Low Shot and Zero Shot training of machine learning without sacrificing accuracy or recall.
http://arxiv.org/abs/1901.06622
We address the problem of designing a conversational avatar capable of a sequence of casual conversations with older adults. Users at risk of loneliness, social anxiety or a sense of ennui may benefit from practicing such conversations in private, at their convenience. We describe an automatic spoken dialogue manager for LISSA, an on-screen virtual agent that can keep older users involved in conversations over several sessions, each lasting 10-20 minutes. The idea behind LISSA is to improve users’ communication skills by providing feedback on their non-verbal behavior at certain points in the course of the conversations. In this paper, we analyze the dialogues collected from the first session between LISSA and each of 8 participants. We examine the quality of the conversations by comparing the transcripts with those collected in a WOZ setting. LISSA’s contributions to the conversations were judged by research assistants who rated the extent to which the contributions were “natural”, “on track”, “encouraging”, “understanding”, “relevant”, and “polite”. The results show that the automatic dialogue manager was able to handle conversation with the users smoothly and naturally.
http://arxiv.org/abs/1901.06620
A crucial challenge in image-based modeling of biomedical data is to identify trends and features that separate normality and pathology. In many cases, the morphology of the imaged object exhibits continuous change as it deviates from normality, and thus a generative model can be trained to model this morphological continuum. Moreover, given side information that correlates to certain trend in morphological change, a latent variable model can be regularized such that its latent representation reflects this side information. In this work, we use the Wasserstein Auto-encoder to model this pathology continuum, and apply the Hilbert-Schmitt Independence Criterion (HSIC) to enforce dependency between certain latent features and the provided side information. We experimentally show that the model can provide disentangled and interpretable latent representations and also generate a continuum of morphological changes that corresponds to change in the side information.
http://arxiv.org/abs/1901.06618
This paper makes the case that while most research on intelligent agents presently centers on the agent and not on the user, the opposite should be true. Covering slot-filling, gaming and chatbot agents, it looks at where the tendency to attend to the agent has come from and why it is important to concentrate more on the user. After reviewing relevant literature, we propose some first approaches to creating and assessing user-centric systems.
http://arxiv.org/abs/1901.06613
Document classification is a challenging task with important applications. Deep learning approaches to the problem have gained much attention. Despite the progress, the proposed models do not incorporate the knowledge of the document structure in the architecture efficiently and not take into account the contexting dependent importance of words and sentences. In this paper, we propose a new approach based on convolutional neural networks, gated recurrent units and attention mechanisms for document classification tasks. The datasets IMDB Movie Reviews and Yelp were used in experiments. The proposed method improves the results of current attention-based approaches
http://arxiv.org/abs/1901.06610
Providing systems the ability to relate linguistic and visual content is one of the hallmarks of computer vision. Tasks such as image captioning and retrieval were designed to test this ability, but come with complex evaluation measures that gauge various other abilities and biases simultaneously. This paper presents an alternative evaluation task for visual-grounding systems: given a caption the system is asked to select the image that best matches the caption from a pair of semantically similar images. The system’s accuracy on this Binary Image SelectiON (BISON) task is not only interpretable, but also measures the ability to relate fine-grained text content in the caption to visual content in the images. We gathered a BISON dataset that complements the COCO Captions dataset and used this dataset in auxiliary evaluations of captioning and caption-based retrieval systems. While captioning measures suggest visual grounding systems outperform humans, BISON shows that these systems are still far away from human performance.
http://arxiv.org/abs/1901.06595
This paper presents an easy and efficient face detection and face recognition approach using free software components from the internet. Face detection and face recognition problems have wide applications in home and office security. Therefore this work will helpful for those searching for a free face off-the-shelf face detection system. Using this system, faces can be detected in uncontrolled environments. In the detection phase, every individual face is detected and in the recognition phase the detected faces are compared with the faces in a given data set and recognized.
http://arxiv.org/abs/1901.06585
With a growing number of social apps, people have become increasingly willing to share their everyday photos and events on social media platforms, such as Facebook, Instagram, and WeChat. In social media data mining, post popularity prediction has received much attention from both data scientists and psychologists. Existing research focuses more on exploring the post popularity on a population of users and including comprehensive factors such as temporal information, user connections, number of comments, and so on. However, these frameworks are not suitable for guiding a specific user to make a popular post because the attributes of this user are fixed. Therefore, previous frameworks can only answer the question “whether a post is popular” rather than “how to become famous by popular posts”. In this paper, we aim at predicting the popularity of a post for a specific user and mining the patterns behind the popularity. To this end, we first collect data from Instagram. We then design a method to figure out the user environment, representing the content that a specific user is very likely to post. Based on the relevant data, we devise a novel dual-attention model to incorporate image, caption, and user environment. The dual-attention model basically consists of two parts, explicit attention for image-caption pairs and implicit attention for user environment. A hierarchical structure is devised to concatenate the explicit attention part and implicit attention part. We conduct a series of experiments to validate the effectiveness of our model and investigate the factors that can influence the popularity. The classification results show that our model outperforms the baselines, and a statistical analysis identifies what kind of pictures or captions can help the user achieve a relatively high “likes” number.
https://arxiv.org/abs/1809.09314
Semantic segmentation remains a computationally intensive algorithm for embedded deployment even with the rapid growth of computation power. Thus efficient network design is a critical aspect especially for applications like automated driving which requires real-time performance. Recently, there has been a lot of research on designing efficient encoders that are mostly task agnostic. Unlike image classification and bounding box object detection tasks, decoders are computationally expensive as well for semantic segmentation task. In this work, we focus on efficient design of the segmentation decoder and assume that an efficient encoder is already designed to provide shared features for a multi-task learning system. We design a novel efficient non-bottleneck layer and a family of decoders which fit into a small run-time budget using VGG10 as efficient encoder. We demonstrate in our dataset that experimentation with various design choices led to an improvement of 10\% from a baseline performance.
http://arxiv.org/abs/1901.06580
The problem of retrosynthetic planning can be framed as one player game, in which the chemist (or a computer program) works backwards from a molecular target to simpler starting materials though a series of choices regarding which reactions to perform. This game is challenging as the combinatorial space of possible choices is astronomical, and the value of each choice remains uncertain until the synthesis plan is completed and its cost evaluated. Here, we address this problem using deep reinforcement learning to identify policies that make (near) optimal reaction choices during each step of retrosynthetic planning. Using simulated experience or self-play, we train neural networks to estimate the expected synthesis cost or value of any given molecule based on a representation of its molecular structure. We show that learned policies based on this value network outperform heuristic approaches in synthesizing unfamiliar molecules from available starting materials using the fewest number of reactions. We discuss how the learned policies described here can be incorporated into existing synthesis planning tools and how they can be adapted to changes in the synthesis cost objective or material availability.
http://arxiv.org/abs/1901.06569
We present consistent optimization for single stage object detection. Previous works of single stage object detectors usually rely on the regular, dense sampled anchors to generate hypothesis for the optimization of the model. Through an examination of the behavior of the detector, we observe that the misalignment between the optimization target and inference configurations has hindered the performance improvement. We propose to bride this gap by consistent optimization, which is an extension of the traditional single stage detector’s optimization strategy. Consistent optimization focuses on matching the training hypotheses and the inference quality by utilizing of the refined anchors during training. To evaluate its effectiveness, we conduct various design choices based on the state-of-the-art RetinaNet detector. We demonstrate it is the consistent optimization, not the architecture design, that yields the performance boosts. Consistent optimization is nearly cost-free, and achieves stable performance gains independent of the model capacities or input scales. Specifically, utilizing consistent optimization improves RetinaNet from 39.1 AP to 40.1 AP on COCO dataset without any bells or whistles, which surpasses the accuracy of all existing state-of-the-art one-stage detectors when adopting ResNet-101 as backbone. The code will be made available.
http://arxiv.org/abs/1901.06563
The paper presents an approach to build a question and answer system that is capable of processing the information in a large dataset and allows the user to gain knowledge from this dataset by asking questions in natural language form. Key content of this research covers four dimensions which are; Corpus Preprocessing, Question Preprocessing, Deep Neural Network for Answer Extraction and Answer Generation. The system is capable of understanding the question, responds to the user’s query in natural language form as well. The goal is to make the user feel as if they were interacting with a person than a machine.
http://arxiv.org/abs/1902.02162
There is a disconnect between explanatory artificial intelligence (XAI) methods and the types of explanations that are useful for and demanded by society (policy makers, government officials, etc.) Questions that experts in artificial intelligence (AI) ask opaque systems provide inside explanations, focused on debugging, reliability, and validation. These are different from those that society will ask of these systems to build trust and confidence in their decisions. Although explanatory AI systems can answer many questions that experts desire, they often don’t explain why they made decisions in a way that is precise (true to the model) and understandable to humans. These outside explanations can be used to build trust, comply with regulatory and policy changes, and act as external validation. In this paper, we focus on XAI methods for deep neural networks (DNNs) because of DNNs’ use in decision-making and inherent opacity. We explore the types of questions that explanatory DNN systems can answer and discuss challenges in building explanatory systems that provide outside explanations for societal requirements and benefit.
http://arxiv.org/abs/1901.06560
Little innovation has been made to low-level attitude flight control used by unmanned aerial vehicles, which still predominantly uses the classical PID controller. In this work we introduce Neuroflight, the first open source neuro-flight controller firmware. We present our toolchain for training a neural network in simulation and compiling it to run on embedded hardware. Challenges faced jumping from simulation to reality are discussed along with our solutions. Our evaluation shows the neural network can execute at over 2.67kHz on an Arm Cortex-M7 processor and flight tests demonstrate a quadcopter running Neuroflight can achieve stable flight and execute aerobatic maneuvers.
http://arxiv.org/abs/1901.06553
Working memory (WM) allows information to be stored and manipulated over short time scales. Performance on WM tasks is thought to be supported by the frontoparietal system (FPS), the default mode system (DMS), and interactions between them. Yet little is known about how these systems and their interactions relate to individual differences in WM performance. We address this gap in knowledge using functional MRI data acquired during the performance of a 2-back WM task, as well as diffusion tensor imaging data collected in the same individuals. We show that the strength of functional interactions between the FPS and DMS during task engagement is inversely correlated with WM performance, and that this strength is modulated by the activation of FPS regions but not DMS regions. Next, we use a clustering algorithm to identify two distinct subnetworks of the FPS, and find that these subnetworks display distinguishable patterns of gene expression. Activity in one subnetwork is positively associated with the strength of FPS-DMS functional interactions, while activity in the second subnetwork is negatively associated. Further, the pattern of structural linkages of these subnetworks explains their differential capacity to influence the strength of FPS-DMS functional interactions. To determine whether these observations could provide a mechanistic account of large-scale neural underpinnings of WM, we build a computational model of the system composed of coupled oscillators. Modulating the amplitude of the subnetworks in the model causes the expected change in the strength of FPS-DMS functional interactions, thereby offering support for a mechanism in which subnetwork activity tunes functional interactions. Broadly, our study presents a holistic account of how regional activity, functional interactions, and structural linkages together support individual differences in WM in humans.
https://arxiv.org/abs/1901.06552
Artificial data synthesis is currently a well studied topic with useful applications in data science, computer vision, graphics and many other fields. Generating realistic data is especially challenging since human perception is highly sensitive to non realistic appearance. In recent times, new levels of realism have been achieved by advances in GAN training procedures and architectures. These successful models, however, are tuned mostly for use with regularly sampled data such as images, audio and video. Despite the successful application of the architecture on these types of media, applying the same tools to geometric data poses a far greater challenge. The study of geometric deep learning is still a debated issue within the academic community as the lack of intrinsic parametrization inherent to geometric objects prohibits the direct use of convolutional filters, a main building block of today’s machine learning systems. In this paper we propose a new method for generating realistic human facial geometries coupled with overlayed textures. We circumvent the parametrization issue by imposing a global mapping from our data to the unit rectangle. We further discuss how to design such a mapping to control the mapping distortion and conserve area within the mapped image. By representing geometric textures and geometries as images, we are able to use advanced GAN methodologies to generate new geometries. We address the often neglected topic of relation between texture and geometry and propose to use this correlation to match between generated textures and their corresponding geometries. We offer a new method for training GAN models on partially corrupted data. Finally, we provide empirical evidence demonstrating our generative model’s ability to produce examples of new identities independent from the training data while maintaining a high level of realism, two traits that are often at odds.
http://arxiv.org/abs/1901.06551
In this work, we introduce the MOldavian and ROmanian Dialectal COrpus (MOROCO), which is freely available for download at https://github.com/butnaruandrei/MOROCO. The corpus contains 33564 samples of text (with over 10 million tokens) collected from the news domain. The samples belong to one of the following six topics: culture, finance, politics, science, sports and tech. The data set is divided into 21719 samples for training, 5921 samples for validation and another 5924 samples for testing. For each sample, we provide corresponding dialectal and category labels. This allows us to perform empirical studies on several classification tasks such as (i) binary discrimination of Moldavian versus Romanian text samples, (ii) intra-dialect multi-class categorization by topic and (iii) cross-dialect multi-class categorization by topic. We perform experiments using a shallow approach based on string kernels, as well as a novel deep approach based on character-level convolutional neural networks containing Squeeze-and-Excitation blocks. We also present and analyze the most discriminative features of our best performing model, before and after named entity removal.
http://arxiv.org/abs/1901.06543
Noise is an important factor which when get added to an image reduces its quality and appearance. So in order to enhance the image qualities, it has to be removed with preserving the textural information and structural features of image. There are different types of noises exist who corrupt the images. Selection of the denoising algorithm is application dependent. Hence, it is necessary to have knowledge about the noise present in the image so as to select the appropriate denoising algorithm. Objective of this paper is to present brief account on types of noises, its types and different noise removal algorithms. In the first section types of noises on the basis of their additive and multiplicative nature are being discussed. In second section a precise classification and analysis of the different potential image denoising algorithm is presented. At the end of paper, a comparative study of all these algorithms in context of performance evaluation is done and concluded with several promising directions for future research work.
http://arxiv.org/abs/1901.06529
When an image is formed, factors such as lighting (spectra, source, and intensity) and camera characteristics (sensor response, lenses) affect the appearance of the image. Therefore, the prime factor that reduces the quality of the image is noise. It hides the important details and information of images. In order to enhance the qualities of the image, the removal of noises become imperative and that should not at the cost of any loss of image information. Noise removal is one of the pre-processing stages of image processing. In this paper a new method for the enhancement of grayscale images is introduced, when images are corrupted by fixed valued impulse noise (salt and pepper noise). The proposed methodology ensures a better output for the low and medium density of fixed value impulse noise as compared to the other famous filters like Standard Median Filter (SMF), Decision Based Median Filter (DBMF) and Modified Decision Based Median Filter (MDBMF) etc. The main objective of the proposed method was to improve peak signal to noise ratio (PSNR), visual perception and reduction in the blurring of the image. The proposed algorithm replaced the noisy pixel by trimmed mean value. When previous pixel values, 0s, and 255s are present in the particular window and all the pixel values are 0s and 255s then the remaining noisy pixels are replaced by mean value. The gray-scale image of mandrill and Lena were tested via the proposed method. The experimental result shows better peak signal to noise ratio (PSNR), mean square error values with better visual and human perception.
http://arxiv.org/abs/1901.06528
Enter the RobotriX, an extremely photorealistic indoor dataset designed to enable the application of deep learning techniques to a wide variety of robotic vision problems. The RobotriX consists of hyperrealistic indoor scenes which are explored by robot agents which also interact with objects in a visually realistic manner in that simulated world. Photorealistic scenes and robots are rendered by Unreal Engine into a virtual reality headset which captures gaze so that a human operator can move the robot and use controllers for the robotic hands; scene information is dumped on a per-frame basis so that it can be reproduced offline to generate raw data and ground truth labels. By taking this approach, we were able to generate a dataset of 38 semantic classes totaling 8M stills recorded at +60 frames per second with full HD resolution. For each frame, RGB-D and 3D information is provided with full annotations in both spaces. Thanks to the high quality and quantity of both raw information and annotations, the RobotriX will serve as a new milestone for investigating 2D and 3D robotic vision tasks with large-scale data-driven techniques.
http://arxiv.org/abs/1901.06514
The area of Handwritten Signature Verification has been broadly researched in the last decades, but remains an open research problem. In offline (static) signature verification, the dynamic information of the signature writing process is lost, and it is difficult to design good feature extractors that can distinguish genuine signatures and skilled forgeries. This verification task is even harder in writer independent scenarios which is undeniably fiscal for realistic cases. In this paper, we have proposed an Ensemble model for offline writer, independent signature verification task with Deep learning. We have used two CNNs for feature extraction, after that RGBT for classification & Stacking to generate final prediction vector. We have done extensive experiments on various datasets from various sources to maintain a variance in the dataset. We have achieved the state of the art performance on various datasets.
http://arxiv.org/abs/1901.06494
Purpose: The facial recess is a delicate structure that must be protected in minimally invasive cochlear implant surgery. Current research estimates the drill trajectory by using endoscopy of the unique mastoid patterns. However, missing depth information limits available features for a registration to preoperative CT data. Therefore, this paper evaluates OCT for enhanced imaging of drill holes in mastoid bone and compares OCT data to original endoscopic images. Methods: A catheter-based OCT probe is inserted into a drill trajectory of a mastoid phantom in a translation-rotation manner to acquire the inner surface state. The images are undistorted and stitched to create volumentric data of the drill hole. The mastoid cell pattern is segmented automatically and compared to ground truth. Results: The mastoid pattern segmented on images acquired with OCT show a similarity of J = 73.6 % to ground truth based on endoscopic images and measured with the Jaccard metric. Leveraged by additional depth information, automated segmentation tends to be more robust and fail-safe compared to endoscopic images. Conclusion: The feasibility of using a clinically approved OCT probe for imaging the drill hole in cochlear implantation is shown. The resulting volumentric images provide additional information on the shape of caveties in the bone structure, which will be useful for image-to-patient registration and to estimate the drill trajectory. This will be another step towards safe minimally invasive cochlear implantation.
http://arxiv.org/abs/1901.06490
We propose an end-to-end affect recognition approach using a Convolutional Neural Network (CNN) that handles multiple languages, with applications to emotion and personality recognition from speech. We lay the foundation of a universal model that is trained on multiple languages at once. As affect is shared across all languages, we are able to leverage shared information between languages and improve the overall performance for each one. We obtained an average improvement of 12.8% on emotion and 10.1% on personality when compared with the same model trained on each language only. It is end-to-end because we directly take narrow-band raw waveforms as input. This allows us to accept as input audio recorded from any source and to avoid the overhead and information loss of feature extraction. It outperforms a similar CNN using spectrograms as input by 12.8% for emotion and 6.3% for personality, based on F-scores. Analysis of the network parameters and layers activation shows that the network learns and extracts significant features in the first layer, in particular pitch, energy and contour variations. Subsequent convolutional layers instead capture language-specific representations through the analysis of supra-segmental features. Our model represents an important step for the development of a fully universal affect recognizer, able to recognize additional descriptors, such as stress, and for the future implementation into affective interactive systems.
http://arxiv.org/abs/1901.06486
In this article, we present an overview of the use of service-oriented architecture and Web services in developing robotics applications and software integrated with the Internet and the Cloud. This is a recent trend that emerged since 2010 from the concept of cloud robotics, which leverages the use of cloud infrastructures for robotics applications following a service-oriented architecture approach. In particular, we distinguish two main categories: (\textit{i.}) virtualization of robotics systems and (\textit{ii.}) computation offloading from robots to cloud-based services. We discuss the main approaches proposed in the literature to design robotics systems through the Web and their integration to the cloud through a service-oriented computing framework.
http://arxiv.org/abs/1901.08173
Spatial resolution is a critical imaging parameter in magnetic resonance imaging (MRI). Acquiring high resolution MRI data usually takes long scanning time and would subject to motion artifacts due to hardware, physical, and physiological limitations. Single image super-resolution (SISR), especially that based on deep learning techniques, is an effective and promising alternative technique to improve the current spatial resolution of magnetic resonance (MR) images. However, the deeper network is more difficult to be effectively trained because the information is gradually weakened as the network deepens. This problem becomes more serious for medical images due to the degradation of training examples. In this paper, we present a novel channel splitting and serial fusion network (CSSFN) for single MR image super-resolution. Specifically, the proposed CSSFN network splits the hierarchical features into a series of subfeatures, which are then integrated together in a serial manner. Thus, the network becomes deeper and can deal with the subfeatures on different channels discriminatively. Besides, a dense global feature fusion (DGFF) is adopted to integrate the intermediate features, which further promotes the information flow in the network. Extensive experiments on several typical MR images show the superiority of our CSSFN model over other advanced SISR methods.
http://arxiv.org/abs/1901.06484
Most of mathematic forgetting curve models fit well with the forgetting data under the learning condition of one time rather than repeated. In the paper, a convolution model of forgetting curve is proposed to simulate the memory process during learning. In this model, the memory ability (i.e. the central procedure in the working memory model) and learning material (i.e. the input in the working memory model) is regarded as the system function and the input function, respectively. The status of forgetting (i.e. the output in the working memory model) is regarded as output function or the convolution result of the memory ability and learning material. The model is applied to simulate the forgetting curves in different situations. The results show that the model is able to simulate the forgetting curves not only in one time learning condition but also in multi-times condition. The model is further verified in the experiments of Mandarin tone learning for Japanese learners. And the predicted curve fits well on the test points.
http://arxiv.org/abs/1901.08114
Despite significant advances in clustering methods in recent years, the outcome of clustering of a natural image dataset is still unsatisfactory due to two important drawbacks. Firstly, clustering of images needs a good feature representation of an image and secondly, we need a robust method which can discriminate these features for making them belonging to different clusters such that intra-class variance is less and inter-class variance is high. Often these two aspects are dealt with independently and thus the features are not sufficient enough to partition the data meaningfully. In this paper, we propose a method where we discover these features required for the separation of the images using deep autoencoder. Our method learns the image representation features automatically for the purpose of clustering and also select a coherent image and an incoherent image simultaneously for a given image so that the feature representation learning can learn better discriminative features for grouping the similar images in a cluster and at the same time separating the dissimilar images across clusters. Experiment results show that our method produces significantly better result than the state-of-the-art methods and we also show that our method is more generalized across different dataset without using any pre-trained model like other existing methods.
http://arxiv.org/abs/1901.06474
We present an analytical study of the quality of metadata about samples used in biomedical experiments. The metadata under analysis are stored in two well-known databases: BioSample—a repository managed by the National Center for Biotechnology Information (NCBI), and BioSamples—a repository managed by the European Bioinformatics Institute (EBI). We tested whether 11.4M sample metadata records in the two repositories are populated with values that fulfill the stated requirements for such values. Our study revealed multiple anomalies in the metadata. Most metadata field names and their values are not standardized or controlled. Even simple binary or numeric fields are often populated with inadequate values of different data types. By clustering metadata field names, we discovered there are often many distinct ways to represent the same aspect of a sample. Overall, the metadata we analyzed reveal that there is a lack of principled mechanisms to enforce and validate metadata requirements. The significant aberrancies that we found in the metadata are likely to impede search and secondary use of the associated datasets.
http://arxiv.org/abs/1808.06907
Physical media (like surveillance cameras) and social media (like Instagram and Twitter) may both be useful in attaining on-the-ground information during an emergency or disaster situation. However, the intersection and reliability of both surveillance cameras and social media during a natural disaster are not fully understood. To address this gap, we tested whether social media is of utility when physical surveillance cameras went off-line during Hurricane Irma in 2017. Specifically, we collected and compared geo-tagged Instagram and Twitter posts in the state of Florida during times and in areas where public surveillance cameras went off-line. We report social media content and frequency and content to determine the utility for emergency managers or first responders during a natural disaster.
http://arxiv.org/abs/1901.06459
This paper was motivated by the problem of how to make robots fuse and transfer their experience so that they can effectively use prior knowledge and quickly adapt to new environments. To address the problem, we present a learning architecture for navigation in cloud robotic systems: Lifelong Federated Reinforcement Learning (LFRLA). In the work, We propose a knowledge fusion algorithm for upgrading a shared model deployed on the cloud. Then, effective transfer learning methods in LFRLA are introduced. LFRLA is consistent with human cognitive science and fits well in cloud robotic systems. Experiments show that LFRLA greatly improves the efficiency of reinforcement learning for robot navigation. The cloud robotic system deployment also shows that LFRLA is capable of fusing prior knowledge. In addition, we release a cloud robotic navigation-learning website based on LFRLA.
http://arxiv.org/abs/1901.06455
Intersections are hazardous places. Threats arise from interactions among pedestrians, bicycles and vehicles, more complicated vehicle trajectories in the absence of lane markings, phases that prevent determining who has the right of way, invisible vehicle approaches, vehicle obstructions, and illegal movements. These challenges are not fully addressed by the “road diet” and road redesign prescribed in Vision Zero plans, nor will they be completely overcome by autonomous vehicles with their many sensors and tireless attention to surroundings. Accidents can also occur because drivers, cyclists and pedestrians do not have the information they need to avoid wrong decisions. In these cases, the missing information can be computed and broadcast by an intelligent intersection. The information gives the current full signal phase, an estimate of the time when the phase will change, and the occupancy of the blind spots of the driver or autonomous vehicle. The paper develops a design of the intelligent intersection, motivated by the analysis of an accident at an intersection in Tempe, AZ, between an automated Uber Volvo and a manual Honda CRV and culminates in a proposal for an intelligent intersection infrastructure. The intelligent intersection also serves as a software-enabled version of the `protected intersection’ design to improve the passage of cyclists and pedestrians through an intersection.
http://arxiv.org/abs/1803.00471
We present a unified framework tackling two problems: class-specific 3D reconstruction from a single image, and generation of new 3D shape samples. These tasks have received considerable attention recently; however, most existing approaches rely on 3D supervision, annotation of 2D images with keypoints or poses, and/or training with multiple views of each object instance. Our framework is very general: it can be trained in similar settings to existing approaches, while also supporting weaker supervision. Importantly, it can be trained purely from 2D images, without pose annotations, and with only a single view per instance. We employ meshes as an output representation, instead of voxels used in most prior work. This allows us to reason over lighting parameters and exploit shading information during training, which previous 2D-supervised methods cannot. Thus, our method can learn to generate and reconstruct concave object classes. We evaluate our approach in various settings, showing that: (i) it learns to disentangle shape from pose and lighting; (ii) using shading in the loss improves performance compared to just silhouettes; (iii) when using a standard single white light, our model outperforms state-of-the-art 2D-supervised methods, both with and without pose supervision, thanks to exploiting shading cues; (iv) performance improves further when using multiple coloured lights, even approaching that of state-of-the-art 3D-supervised methods; (v) shapes produced by our model capture smooth surfaces and fine details better than voxel-based approaches; and (vi) our approach supports concave classes such as bathtubs and sofas, which methods based on silhouettes cannot learn.
http://arxiv.org/abs/1901.06447
We propose a new polar code construction framework (i.e., selecting the frozen bit positions) for the additive white Gaussian noise (AWGN) channel, tailored to a given decoding algorithm, rather than based on the (not necessarily optimal) assumption of successive cancellation (SC) decoding. The proposed framework is based on the Genetic Algorithm (GenAlg), where populations (i.e., collections) of information sets evolve successively via evolutionary transformations based on their individual error-rate performance. These populations converge towards an information set that fits the decoding behavior. Using our proposed algorithm, we construct a polar code of length 2048 with code rate 0.5, without the CRC-aid, tailored to plain successive cancellation list (SCL) decoding, achieving the same error-rate performance as the CRC-aided SCL decoding, and leading to a coding gain of 1 dB at BER of $10^{-6}$. Further, a belief propagation (BP)-tailored polar code approaches the SCL error-rate performance without any modifications in the decoding algorithm itself.
http://arxiv.org/abs/1901.06444
The proliferation of fake news on social media has opened up new directions of research for timely identification and containment of fake news, and mitigation of its widespread impact on public opinion. While much of the earlier research was focused on identification of fake news based on its contents or by exploiting users’ engagements with the news on social media, there has been a rising interest in proactive intervention strategies to counter the spread of misinformation and its impact on society. In this survey, we describe the modern-day problem of fake news and, in particular, highlight the technical challenges associated with it. We discuss existing methods and techniques applicable to both identification and mitigation, with a focus on the significant advances in each method and their advantages and limitations. In addition, research has often been limited by the quality of existing datasets and their specific application contexts. To alleviate this problem, we comprehensively compile and summarize characteristic features of available datasets. Furthermore, we outline new directions of research to facilitate future development of effective and interdisciplinary solutions.
http://arxiv.org/abs/1901.06437
Recently it was shown that linguistic structure predicted by a supervised parser can be beneficial for neural machine translation (NMT). In this work we investigate a more challenging setup: we incorporate sentence structure as a latent variable in a standard NMT encoder-decoder and induce it in such a way as to benefit the translation task. We consider German-English and Japanese-English translation benchmarks and observe that when using RNN encoders the model makes no or very limited use of the structure induction apparatus. In contrast, CNN and word-embedding-based encoders rely on latent graphs and force them to encode useful, potentially long-distance, dependencies.
http://arxiv.org/abs/1901.06436
We present a new methodology for improving the accuracy of small neural networks by applying the concept of a clos network to achieve maximum expression in a smaller network. We explore the design space to show that more layers is beneficial, given the same number of parameters. We also present findings on how the relu nonlinearity ffects accuracy in separable networks. We present results on early work with Cifar-10 dataset.
http://arxiv.org/abs/1901.06433
We present a novel architectural enhancement of Channel Boosting in deep convolutional neural network (CNN). This idea of Channel Boosting exploits both the channel dimension of CNN (learning from multiple input channels) and Transfer learning (TL). TL is utilized at two different stages; channel generation and channel exploitation. In the proposed methodology, a deep CNN is boosted by various channels available through TL from already trained Deep Neural Networks, in addition to its own original channel. The deep architecture of CNN then exploits the original and boosted channels down the stream for learning discriminative patterns. Churn prediction in telecom is a challenging task due to high dimensionality and imbalanced nature of the data and it is therefore used to evaluate the performance of the proposed Channel Boosted CNN (CB CNN). In the first phase, discriminative informative features are being extracted using a staked autoencoder, and then in the second phase, these features are combined with the original features to form Channel Boosted images. Finally, the knowledge gained by a pre trained CNN is exploited by employing TL. The results are promising and show the ability of the Channel Boosting concept in learning complex classification problem by discerning even minute differences in churners and non churners. The proposed work validates the concept observed from the evolution of recent CNN architectures that the innovative restructuring of a CNN architecture may increase the representative capacity of the network.
http://arxiv.org/abs/1804.08528
Adversarially trained deep neural networks have significantly improved performance of single image super resolution, by hallucinating photorealistic local textures, thereby greatly reducing the perception difference between a real high resolution image and its super resolved (SR) counterpart. However, application to medical imaging requires preservation of diagnostically relevant features while refraining from introducing any diagnostically confusing artifacts. We propose using a deep convolutional super resolution network (SRNet) trained for (i) minimising reconstruction loss between the real and SR images, and (ii) maximally confusing learned relativistic visual Turing test (rVTT) networks to discriminate between (a) pair of real and SR images (T1) and (b) pair of patches in real and SR selected from region of interest (T2). The adversarial loss of T1 and T2 while backpropagated through SRNet helps it learn to reconstruct pathorealism in the regions of interest such as white blood cells (WBC) in peripheral blood smears or epithelial cells in histopathology of cancerous biopsy tissues, which are experimentally demonstrated here. Experiments performed for measuring signal distortion loss using peak signal to noise ratio (pSNR) and structural similarity (SSIM) with variation of SR scale factors, impact of rVTT adversarial losses, and impact on reporting using SR on a commercially available artificial intelligence (AI) digital pathology system substantiate our claims.
http://arxiv.org/abs/1901.06405
Fine-grained object recognition concerns the identification of the type of an object among a large number of closely related sub-categories. Multisource data analysis, that aims to leverage the complementary spectral, spatial, and structural information embedded in different sources, is a promising direction towards solving the fine-grained recognition problem that involves low between-class variance, small training set sizes for rare classes, and class imbalance. However, the common assumption of co-registered sources may not hold at the pixel level for small objects of interest. We present a novel methodology that aims to simultaneously learn the alignment of multisource data and the classification model in a unified framework. The proposed method involves a multisource region attention network that computes per-source feature representations, assigns attention scores to candidate regions sampled around the expected object locations by using these representations, and classifies the objects by using an attention-driven multisource representation that combines the feature representations and the attention scores from all sources. All components of the model are realized using deep neural networks and are learned in an end-to-end fashion. Experiments using RGB, multispectral, and LiDAR elevation data for classification of street trees showed that our approach achieved 64.2% and 47.3% accuracies for the 18-class and 40-class settings, respectively, which correspond to 13% and 14.3% improvement relative to the commonly used feature concatenation approach from multiple sources.
http://arxiv.org/abs/1901.06403
We have shown previously that our parameter-reduced variants of Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNN) are comparable in performance to the standard LSTM RNN on the MNIST dataset. In this study, we show that this is also the case for two diverse benchmark datasets, namely, the review sentiment IMDB and the 20 Newsgroup datasets. Specifically, we focus on two of the simplest variants, namely LSTM_6 (i.e., standard LSTM with three constant fixed gates) and LSTM_C6 (i.e., LSTM_6 with further reduced cell body input block). We demonstrate that these two aggressively reduced-parameter variants are competitive with the standard LSTM when hyper-parameters, e.g., learning parameter, number of hidden units and gate constants are set properly. These architectures enable speeding up training computations and hence, these networks would be more suitable for online training and inference onto portable devices with relatively limited computational resources.
http://arxiv.org/abs/1901.06401
We contemplate a higher-level bipolar abstract argumentation for non-elementary arguments such as: X argues against Ys sincerity with the fact that Y has presented his argument to draw a conclusion C, by omitting other facts which would not have validated C. Argumentation involving such arguments requires us to potentially consider an argument as a coherent block of argumentation, i.e. an argument may itself be an argumentation. In this work, we formulate block argumentation as a specific instance of Dung-style bipolar abstract argumentation with the dual nature of arguments. We consider internal consistency of an argument(ation) under a set of constraints, of graphical (syntactic) and of semantic nature, and formulate acceptability semantics in relation to them. We discover that classical acceptability semantics do not in general hold good with the constraints. In particular, acceptability of unattacked arguments is not always warranted. Further, there may not be a unique minimal member in complete semantics, thus sceptic (grounded) semantics may not be its subset. To retain set-theoretically minimal semantics as a subset of complete semantics, we define semi-grounded semantics. Through comparisons, we show how the concept of block argumentation may further generalise structured argumentation.
http://arxiv.org/abs/1901.06378
Automatic lesion detection from computed tomography (CT) scans is an important task in medical imaging analysis. It is still very challenging due to similar appearances (e.g. intensity and texture) between lesions and other tissues, making it especially difficult to develop a universal lesion detector. Instead of developing a specific-type lesion detector, this work builds a Universal Lesion Detector (ULDor) based on Mask R-CNN, which is able to detect all different kinds of lesions from whole body parts. As a state-of-the-art object detector, Mask R-CNN adds a branch for predicting segmentation masks on each Region of Interest (RoI) to improve the detection performance. However, it is almost impossible to manually annotate a large-scale dataset with pixel-level lesion masks to train the Mask R-CNN for lesion detection. To address this problem, this work constructs a pseudo mask for each lesion region that can be considered as a surrogate of the real mask, based on which the Mask R-CNN is employed for lesion detection. On the other hand, this work proposes a hard negative example mining strategy to reduce the false positives for improving the detection performance. Experimental results on the NIH DeepLesion dataset demonstrate that the ULDor is enhanced using pseudo masks and the proposed hard negative example mining strategy and achieves a sensitivity of 86.21% with five false positives per image.
http://arxiv.org/abs/1901.06359