We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages. Our model only relies on the Bible, a considerably smaller parallel data than the commonly used parallel data in transfer methods. We use the concatenation of projected trees from the Bible corpus, and the gold-standard treebanks in multiple source languages along with cross-lingual word representations. We demonstrate that reordering the source treebanks before training on them for a target language improves the accuracy of languages outside the European language family. Our experiments on 68 treebanks (38 languages) in the Universal Dependencies corpus achieve a high accuracy for all languages. Among them, our experiments on 16 treebanks of 12 non-European languages achieve an average UAS absolute improvement of 3.3% over a state-of-the-art method.
http://arxiv.org/abs/1903.05683
Generative Adversarial Networks (GANs) have become exceedingly popular in a wide range of data-driven research fields, due in part to their success in image generation. Their ability to generate new samples, often from only a small amount of input data, makes them an exciting research tool in areas with limited data resources. One less-explored application of GANs is the synthesis of speech and audio samples. Herein, we propose a set of extensions to the WaveGAN paradigm, a recently proposed approach for sound generation using GANs. The aim of these extensions - preprocessing, Audio-to-Audio generation, skip connections and progressive structures - is to improve the human likeness of synthetic speech samples. Scores from listening tests with 30 volunteers demonstrated a moderate improvement (Cohen’s d coefficient of 0.65) in human likeness using the proposed extensions compared to the original WaveGAN approach.
http://arxiv.org/abs/1903.07395
Inferring a person’s goal from their behavior is an important problem in applications of AI (e.g. automated assistants, recommender systems). The workhorse model for this task is the rational actor model - this amounts to assuming that people have stable reward functions, discount the future exponentially, and construct optimal plans. Under the rational actor assumption techniques such as inverse reinforcement learning (IRL) can be used to infer a person’s goals from their actions. A competing model is the dual-system model. Here decisions are the result of an interplay between a fast, automatic, heuristic-based system 1 and a slower, deliberate, calculating system 2. We generalize the dual system framework to the case of Markov decision problems and show how to compute optimal plans for dual-system agents. We show that dual-system agents exhibit behaviors that are incompatible with rational actor assumption. We show that naive applications of rational-actor IRL to the behavior of dual-system agents can generate wrong inference about the agents’ goals and suggest interventions that actually reduce the agent’s overall utility. Finally, we adapt a simple IRL algorithm to correctly infer the goals of dual system decision-makers. This allows us to make interventions that help, rather than hinder, the dual-system agent’s ability to reach their true goals.
http://arxiv.org/abs/1811.08549
Image-to-image translation has recently received significant attention due to advances in deep learning. Most works focus on learning either a one-to-one mapping in an unsupervised way or a many-to-many mapping in a supervised way. However, a more practical setting is many-to-many mapping in an unsupervised way, which is harder due to the lack of supervision and the complex inner- and cross-domain variations. To alleviate these issues, we propose the Exemplar Guided & Semantically Consistent Image-to-image Translation (EGSC-IT) network which conditions the translation process on an exemplar image in the target domain. We assume that an image comprises of a content component which is shared across domains, and a style component specific to each domain. Under the guidance of an exemplar from the target domain we apply Adaptive Instance Normalization to the shared content component, which allows us to transfer the style information of the target domain to the source domain. To avoid semantic inconsistencies during translation that naturally appear due to the large inner- and cross-domain variations, we introduce the concept of feature masks that provide coarse semantic guidance without requiring the use of any semantic labels. Experimental results on various datasets show that EGSC-IT does not only translate the source image to diverse instances in the target domain, but also preserves the semantic consistency during the process.
http://arxiv.org/abs/1805.11145
Deep convolutional neural networks (CNNs) show strong promise for analyzing scientific data in many domains including particle imaging detectors such as a liquid argon time projection chamber (LArTPC). Yet the high sparsity of LArTPC data challenges traditional CNNs which were designed for dense data such as photographs. A naive application of CNNs on LArTPC data results in inefficient computations and a poor scalability to large LArTPC detectors such as the Short Baseline Neutrino Program and Deep Underground Neutrino Experiment. Recently Submanifold Sparse Convolutional Networks (SSCNs) have been proposed to address this challenge. We report their performance on a 3D semantic segmentation task on simulated LArTPC samples. In comparison with standard CNNs, we observe that the computation memory and wall-time cost for inference are reduced by factor of 364 and 33 respectively without loss of accuracy. The same factors for 2D samples are found to be 93 and 3.1 respectively. Using SSCN, we present the first machine learning-based approach to the reconstruction of Michel electrons using public 3D LArTPC samples. We find a Michel electron identification efficiency of 93.9\% with 98.8\% of true positive rate. Reconstructed Michel electron clusters yield 96.1\% in average pixel clustering efficiency and 97.3\% in purity. The results are compelling to show strong promise of scalable data reconstruction technique using deep neural networks for large scale LArTPC detectors.
http://arxiv.org/abs/1903.05663
In this paper, we introduce the Phoenix drone: the first completely open-source tail-sitter micro aerial vehicle (MAV) platform. The vehicle has a highly versatile, dual-rotor design and is engineered to be low-cost and easily extensible/modifiable. Our open-source release includes all of the design documents, software resources, and simulation tools needed to build and fly a high-performance tail-sitter for research and educational purposes. The drone has been developed for precision flight with a high degree of control authority. Our design methodology included extensive testing and characterization of the aerodynamic properties of the vehicle. The platform incorporates many off-the-shelf components and 3D-printed parts, in order to keep the cost down. Nonetheless, the paper includes results from flight trials which demonstrate that the vehicle is capable of very stable hovering and accurate trajectory tracking. Our hope is that the open-source Phoenix reference design will be useful to both researchers and educators. In particular, the details in this paper and the available open-source materials should enable learners to gain an understanding of aerodynamics, flight control, state estimation, software design, and simulation, while experimenting with a unique aerial robot.
http://arxiv.org/abs/1810.03196
Nowadays, autonomous service robots are becoming an important topic in robotic research. Differently from typical industrial scenarios, with highly controlled environments, service robots must show an additional robustness to task perturbations and changes in the characteristics of their sensory feedback. In this paper a robot is taught to perform two different cleaning tasks over a table, using a learning from demonstration paradigm. However, differently from other approaches, a convolutional neural network is used to generalize the demonstrations to different, not yet seen dirt or stain patterns on the same table using only visual feedback, and to perform cleaning movements accordingly. Robustness to robot posture and illumination changes is achieved using data augmentation techniques and camera images transformation. This robustness allows the transfer of knowledge regarding execution of cleaning tasks between heterogeneous robots operating in different environmental settings. To demonstrate the viability of the proposed approach, a network trained in Lisbon to perform cleaning tasks, using the iCub robot, is successfully employed by the DoRo robot in Peccioli, Italy.
http://arxiv.org/abs/1903.05635
Most conditional generation tasks expect diverse outputs given a single conditional context. However, conditional generative adversarial networks (cGANs) often focus on the prior conditional information and ignore the input noise vectors, which contribute to the output variations. Recent attempts to resolve the mode collapse issue for cGANs are usually task-specific and computationally expensive. In this work, we propose a simple yet effective regularization term to address the mode collapse issue for cGANs. The proposed method explicitly maximizes the ratio of the distance between generated images with respect to the corresponding latent codes, thus encouraging the generators to explore more minor modes during training. This mode seeking regularization term is readily applicable to various conditional generation tasks without imposing training overhead or modifying the original network structures. We validate the proposed algorithm on three conditional image synthesis tasks including categorical generation, image-to-image translation, and text-to-image synthesis with different baseline models. Both qualitative and quantitative results demonstrate the effectiveness of the proposed regularization method for improving diversity without loss of quality.
http://arxiv.org/abs/1903.05628
In order for artificial agents to coordinate effectively with people, they must act consistently with existing conventions (e.g. how to navigate in traffic, which language to speak, or how to coordinate with teammates). A group’s conventions can be viewed as a choice of equilibrium in a coordination game. We consider the problem of an agent learning a policy for a coordination game in a simulated environment and then using this policy when it enters an existing group. When there are multiple possible conventions we show that learning a policy via multi-agent reinforcement learning (MARL) is likely to find policies which achieve high payoffs at training time but fail to coordinate with the real group into which the agent enters. We assume access to a small number of samples of behavior from the true convention and show that we can augment the MARL objective to help it find policies consistent with the real group’s convention. In three environments from the literature - traffic, communication, and team coordination - we observe that augmenting MARL with a small amount of imitation learning greatly increases the probability that the strategy found by MARL fits well with the existing social convention. We show that this works even in an environment where standard training methods very rarely find the true convention of the agent’s partners.
http://arxiv.org/abs/1806.10071
The problem of tracking multiple objects in a video sequence poses several challenging tasks. For tracking-by-detection these include, among others, object re-identification, motion prediction and dealing with occlusions. We present a tracker without bells and whistles that accomplishes tracking without specifically targeting any of these tasks, in particular, we perform no training or optimization on tracking data. To this end, we exploit the bounding box regression of an object detector to predict an object’s new position in the next frame, thereby converting a detector into a Tracktor. We demonstrate the extensibility of our Tracktor and provide a new state-of-the-art on three multi-object tracking benchmarks by extending it with a straightforward re-identification and camera motion compensation. We then perform an analysis on the performance and failure cases of several state-of-the-art tracking methods and our Tracktor. Surprisingly, none of the dedicated tracking methods are considerably better in dealing with complex tracking scenarios, namely, small and occluded objects or missing detections. However, our approach tackles most of the easy tracking scenarios. Therefore, we motivate our approach as a new tracking paradigm and point out promising future research directions. Overall, we show that a cleverly exploited detector can perform better tracking than any current tracking method and expose the real tracking challenges which are still unsolved.
http://arxiv.org/abs/1903.05625
Word meaning changes over time, depending on linguistic and extra-linguistic factors. Associating a word’s correct meaning in its historical context is a critical challenge in diachronic research, and is relevant to a range of NLP tasks, including information retrieval and semantic search in historical texts. Bayesian models for semantic change have emerged as a powerful tool to address this challenge, providing explicit and interpretable representations of semantic change phenomena. However, while corpora typically come with rich metadata, existing models are limited by their inability to exploit contextual information (such as text genre) beyond the document time-stamp. This is particularly critical in the case of ancient languages, where lack of data and long diachronic span make it harder to draw a clear distinction between polysemy and semantic change, and current systems perform poorly on these languages. We develop GASC, a dynamic semantic change model that leverages categorical metadata about the texts’ genre information to boost inference and uncover the evolution of meanings in Ancient Greek corpora. In a new evaluation framework, we show that our model achieves improved predictive performance compared to the state of the art.
http://arxiv.org/abs/1903.05587
In this paper, we present exploitability descent, a new algorithm to compute approximate equilibria in two-player zero-sum extensive-form games with imperfect information, by direct policy optimization against worst-case opponents. We prove that when following this optimization, the exploitability of a player’s strategy converges asymptotically to zero, and hence when both players employ this optimization, the joint policies converge to a Nash equilibrium. Unlike fictitious play (XFP) and counterfactual regret minimization (CFR), our convergence result pertains to the policies being optimized rather than the average policies. Our experiments demonstrate convergence rates comparable to XFP and CFR in four benchmark games in the tabular case. Using function approximation, we find that our algorithm outperforms the tabular version in two of the games, which, to the best of our knowledge, is the first such result in imperfect information games among this class of algorithms.
http://arxiv.org/abs/1903.05614
Multiple object video object segmentation is a challenging task, specially for the zero-shot case, when no object mask is given at the initial frame and the model has to find the objects to be segmented along the sequence. In our work, we propose a Recurrent network for multiple object Video Object Segmentation (RVOS) that is fully end-to-end trainable. Our model incorporates recurrence on two different domains: (i) the spatial, which allows to discover the different object instances within a frame, and (ii) the temporal, which allows to keep the coherence of the segmented objects along time. We train RVOS for zero-shot video object segmentation and are the first ones to report quantitative results for DAVIS-2017 and YouTube-VOS benchmarks. Further, we adapt RVOS for one-shot video object segmentation by using the masks obtained in previous time steps as inputs to be processed by the recurrent module. Our model reaches comparable results to state-of-the-art techniques in YouTube-VOS benchmark and outperforms all previous video object segmentation methods not using online learning in the DAVIS-2017 benchmark. Moreover, our model achieves faster inference runtimes than previous methods, reaching 44ms/frame on a P100 GPU.
http://arxiv.org/abs/1903.05612
Low-rankness of amplitude spectrograms has been effectively utilized in audio signal processing methods including non-negative matrix factorization. However, such methods have a fundamental limitation owing to their amplitude-only treatment where the phase of the observed signal is utilized for resynthesizing the estimated signal. In order to address this limitation, we directly treat a complex-valued spectrogram and show a complex-valued spectrogram of a sum of sinusoids can be approximately low-rank by modifying its phase. For evaluating the applicability of the proposed low-rank representation, we further propose a convex prior emphasizing harmonic signals, and it is applied to audio denoising.
http://arxiv.org/abs/1903.05603
Decomposition of an audio mixture into harmonic and percussive components, namely harmonic/percussive source separation (HPSS), is a useful pre-processing tool for many audio applications. Popular approaches to HPSS exploit the distinctive source-specific structures of power spectrograms. However, such approaches consider only power spectrograms, and the phase remains intact for resynthesizing the separated signals. In this paper, we propose a phase-aware HPSS method based on the structure of the phase of harmonic components. It is formulated as a convex optimization problem in the time domain, which enables the simultaneous treatment of both amplitude and phase. The numerical experiment validates the effectiveness of the proposed method.
http://arxiv.org/abs/1903.05600
Recently, privacy has a growing importance in several domains, especially in street-view images. The conventional way to achieve this is to automatically detect and blur sensitive information from these images. However, the processing cost of blurring increases with the ever-growing resolution of images. We propose a system that is cost-effective even after increasing the resolution by a factor of 2.5. The new system utilizes depth data obtained from LiDAR to significantly reduce the search space for detection, thereby reducing the processing cost. Besides this, we test several detectors after reducing the detection space and provide an alternative solution based on state-of-the-art deep learning detectors to the existing HoG-SVM-Deep system that is faster and has a higher performance.
http://arxiv.org/abs/1903.05598
Data augmentation is a popular technique which helps improve generalization capabilities of deep neural networks. It plays a pivotal role in remote-sensing scenarios in which the amount of high-quality ground truth data is limited, and acquiring new examples is costly or impossible. This is a common problem in hyperspectral imaging, where manual annotation of image data is difficult, expensive, and prone to human bias. In this letter, we propose online data augmentation of hyperspectral data which is executed during the inference rather than before the training of deep networks. This is in contrast to all other state-of-the-art hyperspectral augmentation algorithms which increase the size (and representativeness) of training sets. Additionally, we introduce a new principal component analysis based augmentation. The experiments revealed that our data augmentation algorithms improve generalization of deep networks, work in real-time, and the online approach can be effectively combined with offline techniques to enhance the classification accuracy.
http://arxiv.org/abs/1903.05580
We study the video super-resolution (SR) problem not for visual quality, but for facilitating video analytics tasks, e.g. action recognition. The popular action recognition methods based on convolutional networks, exemplified by two-stream networks, are not directly applicable on videos of different spatial resolutions. This can be remedied by performing video SR prior to recognition, which motivates us to improve the SR procedure for recognition accuracy. Tailored for two-stream action recognition networks, we propose two video SR methods for the spatial and temporal streams respectively. On the one hand, we observe that the added details by image SR methods can be either helpful or harmful for recognition, and we propose an optical-flow guided weighted mean-squared-error loss for our spatial-oriented SR (SoSR) network. On the other hand, we observe that existing video SR methods incur temporal discontinuity between frames, which also worsens the recognition accuracy, and we propose a siamese network for our temporal-oriented SR (ToSR) that emphasizes the temporal continuity between consecutive frames. We perform experiments using two state-of-the-art action recognition networks and two well-known datasets–UCF101 and HMDB51. Results demonstrate the effectiveness of our proposed SoSR and ToSR in improving recognition accuracy.
http://arxiv.org/abs/1903.05577
Image-based localization is a core component of many augmented/mixed reality (AR/MR) and autonomous robotic systems. Current localization systems rely on the persistent storage of 3D point clouds of the scene to enable camera pose estimation, but such data reveals potentially sensitive scene information. This gives rise to significant privacy risks, especially as for many applications 3D mapping is a background process that the user might not be fully aware of. We pose the following question: How can we avoid disclosing confidential information about the captured 3D scene, and yet allow reliable camera pose estimation? This paper proposes the first solution to what we call privacy preserving image-based localization. The key idea of our approach is to lift the map representation from a 3D point cloud to a 3D line cloud. This novel representation obfuscates the underlying scene geometry while providing sufficient geometric constraints to enable robust and accurate 6-DOF camera pose estimation. Extensive experiments on several datasets and localization scenarios underline the high practical relevance of our proposed approach.
http://arxiv.org/abs/1903.05572
We have recently seen the emergence of several publicly available Natural Language Understanding (NLU) toolkits, which map user utterances to structured, but more abstract, Dialogue Act (DA) or Intent specifications, while making this process accessible to the lay developer. In this paper, we present the first wide coverage evaluation and comparison of some of the most popular NLU services, on a large, multi-domain (21 domains) dataset of 25K user utterances that we have collected and annotated with Intent and Entity Type specifications and which will be released as part of this submission. The results show that on Intent classification Watson significantly outperforms the other platforms, namely, Dialogflow, LUIS and Rasa; though these also perform well. Interestingly, on Entity Type recognition, Watson performs significantly worse due to its low Precision. Again, Dialogflow, LUIS and Rasa perform well on this task.
http://arxiv.org/abs/1903.05566
We develop a connection sensitive attention U-Net(CSAU) for accurate retinal vessel segmentation. This method improves the recent attention U-Net for semantic segmentation with four key improvements: (1) connection sensitive loss that models the structure properties to improve the accuracy of pixel-wise segmentation; (2) attention gate with novel neural network structure and concatenating DOWN-Link to effectively learn better attention weights on fine vessels; (3) integration of connection sensitive loss and attention gate to further improve the accuracy on detailed vessels by additionally concatenating attention weights to features before output; (4) metrics of connection sensitive accuracy to reflect the segmentation performance on boundaries and thin vessels. Our method can effectively improve state-of-the-art vessel segmentation methods that suffer from difficulties in presence of abnormalities, bifurcation and microvascular. This connection sensitive loss tightly integrates with the proposed attention U-Net to accurately (i) segment retinal vessels, and (ii) reserve the connectivity of thin vessels by modeling the structural properties. Our method achieves the leading position on DRIVE, STARE and HRF datasets among the state-of-the-art methods.
http://arxiv.org/abs/1903.05558
This paper describes a baseline for the second iteration of the Fact Extraction and VERification shared task (FEVER2.0) which explores the resilience of systems through adversarial evaluation. We present a collection of simple adversarial attacks against systems that participated in the first FEVER shared task. FEVER modeled the assessment of truthfulness of written claims as a joint information retrieval and natural language inference task using evidence from Wikipedia. A large number of participants made use of deep neural networks in their submissions to the shared task. The extent as to whether such models understand language has been the subject of a number of recent investigations and discussion in literature. In this paper, we present a simple method of generating entailment-preserving and entailment-altering perturbations of instances by common patterns within the training data. We find that a number of systems are greatly affected with absolute losses in classification accuracy of up to $29\%$ on the newly perturbed instances. Using these newly generated instances, we construct a sample submission for the FEVER2.0 shared task. Addressing these types of attacks will aid in building more robust fact-checking models, as well as suggest directions to expand the datasets.
http://arxiv.org/abs/1903.05543
This paper describes, develops, and validates SciLens, a method to evaluate the quality of scientific news articles. The starting point for our work are structured methodologies that define a series of quality aspects for manually evaluating news. Based on these aspects, we describe a series of indicators of news quality. According to our experiments, these indicators help non-experts evaluate more accurately the quality of a scientific news article, compared to non-experts that do not have access to these indicators. Furthermore, SciLens can also be used to produce a completely automated quality score for an article, which agrees more with expert evaluators than manual evaluations done by non-experts. One of the main elements of SciLens is the focus on both content and context of articles, where context is provided by (1) explicit and implicit references on the article to scientific literature, and (2) reactions in social media referencing the article. We show that both contextual elements can be valuable sources of information for determining article quality. The validation of SciLens, done through a combination of expert and non-expert annotation, demonstrates its effectiveness for both semi-automatic and automatic quality evaluation of scientific news.
http://arxiv.org/abs/1903.05538
We present experimental results using a passive whole-body control approach for quadruped robots that achieves dynamic locomotion while compliantly balancing the robot’s trunk. We formulate the motion tracking as a Quadratic Program (QP) that takes into account the full robot rigid body dynamics, the actuation limits, the joint limits and the contact interaction. We analyze the controller’s robustness against inaccurate friction coefficient estimates and unstable footholds, as well as its capability to redistribute the load as a consequence of enforcing actuation limits. Additionally, we present practical implementation details gained from the experience with the real platform. Extensive experimental trials on the 90 kg Hydraulically actuated Quadruped (HyQ) robot validate the capabilities of this controller under various terrain conditions and gaits. The proposed approach is superior for accurate execution of highly dynamic motions with respect to the current state of the art.
http://arxiv.org/abs/1811.00884
Belief space planning is a viable alternative to formalise partially observable control problems and, in the recent years, its application to robot manipulation problems has grown. However, this planning approach was tried successfully only on simplified control problems. In this paper, we apply belief space planning to the problem of planning dexterous reach-to-grasp trajectories under object pose uncertainty. In our framework, the robot perceives the object to be grasped on-the-fly as a point cloud and compute a full 6D, non-Gaussian distribution over the object’s pose (our belief space). The system has no limitations on the geometry of the object, i.e., non-convex objects can be represented, nor assumes that the point cloud is a complete representation of the object. A plan in the belief space is then created to reach and grasp the object, such that the information value of expected contacts along the trajectory is maximised to compensate for the pose uncertainty. If an unexpected contact occurs when performing the action, such information is used to refine the pose distribution and triggers a re-planning. Experimental results show that our planner (IR3ne) improves grasp reliability and compensates for the pose uncertainty such that it doubles the proportion of grasps that succeed on a first attempt.
http://arxiv.org/abs/1903.05517
This paper presents a hardness-aware deep metric learning (HDML) framework. Most previous deep metric learning methods employ the hard negative mining strategy to alleviate the lack of informative samples for training. However, this mining strategy only utilizes a subset of training data, which may not be enough to characterize the global geometry of the embedding space comprehensively. To address this problem, we perform linear interpolation on embeddings to adaptively manipulate their hard levels and generate corresponding label-preserving synthetics for recycled training, so that information buried in all samples can be fully exploited and the metric is always challenged with proper difficulty. Our method achieves very competitive performance on the widely used CUB-200-2011, Cars196, and Stanford Online Products datasets.
http://arxiv.org/abs/1903.05503
Deep learning techniques are rapidly advanced recently, and becoming a necessity component for widespread systems. However, the inference process of deep learning is black-box, and not very suitable to safety-critical systems which must exhibit high transparency. In this paper, to address this black-box limitation, we develop a simple analysis method which consists of 1) structural feature analysis: lists of the features contributing to inference process, 2) linguistic feature analysis: lists of the natural language labels describing the visual attributes for each feature contributing to inference process, and 3) consistency analysis: measuring consistency among input data, inference (label), and the result of our structural and linguistic feature analysis. Our analysis is simplified to reflect the actual inference process for high transparency, whereas it does not include any additional black-box mechanisms such as LSTM for highly human readable results. We conduct experiments and discuss the results of our analysis qualitatively and quantitatively, and come to believe that our work improves the transparency of neural networks. Evaluated through 12,800 human tasks, 75% workers answer that input data and result of our feature analysis are consistent, and 70% workers answer that inference (label) and result of our feature analysis are consistent. In addition to the evaluation of the proposed analysis, we find that our analysis also provide suggestions, or possible next actions such as expanding neural network complexity or collecting training data to improve a neural network.
http://arxiv.org/abs/1903.05501
Reliable obstacle detection and classification in rough and unstructured terrain such as agricultural fields or orchards remains a challenging problem. These environments involve large variations in both geometry and appearance, challenging perception systems that rely on only a single sensor modality. Geometrically, tall grass, fallen leaves, or terrain roughness can mistakenly be perceived as nontraversable or might even obscure actual obstacles. Likewise, traversable grass or dirt roads and obstacles such as trees and bushes might be visually ambiguous. In this paper, we combine appearance- and geometry-based detection methods by probabilistically fusing lidar and camera sensing with semantic segmentation using a conditional random field. We apply a state-of-the-art multimodal fusion algorithm from the scene analysis domain and adjust it for obstacle detection in agriculture with moving ground vehicles. This involves explicitly handling sparse point cloud data and exploiting both spatial, temporal, and multimodal links between corresponding 2D and 3D regions. The proposed method was evaluated on a diverse data set, comprising a dairy paddock and different orchards gathered with a perception research robot in Australia. Results showed that for a two-class classification problem (ground and nonground), only the camera leveraged from information provided by the other modality with an increase in the mean classification score of 0.5%. However, as more classes were introduced (ground, sky, vegetation, and object), both modalities complemented each other with improvements of 1.4% in 2D and 7.9% in 3D. Finally, introducing temporal links between successive frames resulted in improvements of 0.2% in 2D and 1.5% in 3D.
http://arxiv.org/abs/1706.02908
Ugglan is a system designed to discover named entities and link them to unique identifiers in a knowledge base. It is based on a combination of a name and nominal dictionary derived from Wikipedia and Wikidata, a named entity recognition module (NER) using fixed ordinally-forgetting encoding (FOFE) trained on the TAC EDL data from 2014-2016, a candidate generation module from the Wikipedia link graph across multiple editions, a PageRank link and cooccurrence graph disambiguator, and finally a reranker trained on the TAC EDL 2015-2016 data.
http://arxiv.org/abs/1903.05498
We present MMKG, a collection of three knowledge graphs that contain both numerical features and (links to) images for all entities as well as entity alignments between pairs of KGs. Therefore, multi-relational link prediction and entity matching communities can benefit from this resource. We believe this data set has the potential to facilitate the development of novel multi-modal learning approaches for knowledge graphs.We validate the utility ofMMKG in the sameAs link prediction task with an extensive set of experiments. These experiments show that the task at hand benefits from learning of multiple feature types.
http://arxiv.org/abs/1903.05485
In this work, we present a camera geopositioning system based on matching a query image against a database with panoramic images. For matching, our system uses memory vectors aggregated from global image descriptors based on convolutional features to facilitate fast searching in the database. To speed up searching, a clustering algorithm is used to balance geographical positioning and computation time. We refine the obtained position from the query image using a new outlier removal algorithm. The matching of the query image is obtained with a recall@5 larger than 90% for panorama-to-panorama matching. We cluster available panoramas from geographically adjacent locations into a single compact representation and observe computational gains of approximately 50% at the cost of only a small (approximately 3%) recall loss. Finally, we present a coordinate estimation algorithm that reduces the median geopositioning error by up to 20%.
http://arxiv.org/abs/1903.05454
Financial market forecasting is one of the most attractive practical applications of sentiment analysis. In this paper, we investigate the potential of using sentiment \emph{attitudes} (positive vs negative) and also sentiment \emph{emotions} (joy, sadness, etc.) extracted from financial news or tweets to help predict stock price movements. Our extensive experiments using the \emph{Granger-causality} test have revealed that (i) in general sentiment attitudes do not seem to Granger-cause stock price changes; and (ii) while on some specific occasions sentiment emotions do seem to Granger-cause stock price changes, the exhibited pattern is not universal and must be looked at on a case by case basis. Furthermore, it has been observed that at least for certain stocks, integrating sentiment emotions as additional features into the machine learning based market trend prediction model could improve its accuracy.
http://arxiv.org/abs/1903.05440
Visual semantic information comprises two important parts: the meaning of each visual semantic unit and the coherent visual semantic relation conveyed by these visual semantic units. Essentially, the former one is a visual perception task while the latter one corresponds to visual context reasoning. Remarkable advances in visual perception have been achieved due to the success of deep learning. In contrast, visual semantic information pursuit, a visual scene semantic interpretation task combining visual perception and visual context reasoning, is still in its early stage. It is the core task of many different computer vision applications, such as object detection, visual semantic segmentation, visual relationship detection or scene graph generation. Since it helps to enhance the accuracy and the consistency of the resulting interpretation, visual context reasoning is often incorporated with visual perception in current deep end-to-end visual semantic information pursuit methods. However, a comprehensive review for this exciting area is still lacking. In this survey, we present a unified theoretical paradigm for all these methods, followed by an overview of the major developments and the future trends in each potential direction. The common benchmark datasets, the evaluation metrics and the comparisons of the corresponding methods are also introduced.
http://arxiv.org/abs/1903.05434
Depth completion involves estimating a dense depth image from sparse depth measurements, often guided by a color image. While linear upsampling is straight forward, it results in artifacts including depth pixels being interpolated in empty space across discontinuities between objects. Current methods use deep networks to upsample and “complete” the missing depth pixels. Nevertheless, depth smearing between objects remains a challenge. We propose a new representation for depth called Depth Coefficients (DC) to address this problem. It enables convolutions to more easily avoid inter-object depth mixing. We also show that the standard Mean Squared Error (MSE) loss function can promote depth mixing, and thus propose instead to use cross-entropy loss for DC. With quantitative and qualitative evaluation on benchmarks, we show that switching out sparse depth input and MSE loss with our DC representation and cross-entropy loss is a simple way to improve depth completion performance, and reduce pixel depth mixing, which leads to improved depth-based object detection.
http://arxiv.org/abs/1903.05421
This paper introduces improved methods for sub-event detection in social media streams, by applying neural sequence models not only on the level of individual posts, but also directly on the stream level. Current approaches to identify sub-events within a given event, such as a goal during a soccer match, essentially do not exploit the sequential nature of social media streams. We address this shortcoming by framing the sub-event detection problem in social media streams as a sequence labeling task and adopt a neural sequence architecture that explicitly accounts for the chronological order of posts. Specifically, we (i) establish a neural baseline that outperforms a graph-based state-of-the-art method for binary sub-event detection (2.7% micro-F1 improvement), as well as (ii) demonstrate superiority of a recurrent neural network model on the posts sequence level for labeled sub-events (2.4% bin-level F1 improvement over non-sequential models).
http://arxiv.org/abs/1903.05396
In this work, we present a novel automated procedure for constructing a metric map of an unknown domain with obstacles using uncertain position data collected by a swarm of resource-constrained robots. The robots obtain this data during random exploration of the domain by combining onboard odometry information with noisy measurements of signals received from transmitters located outside the domain. This data is processed offline to compute a density function of the free space over a discretization of the domain. We use persistent homology techniques from topological data analysis to estimate a value for thresholding the density function, thereby segmenting the obstacle-occupied region in the unknown domain. Our approach is substantiated with theoretical results to prove its completeness and to analyze its time complexity. The effectiveness of the procedure is illustrated with numerical simulations conducted on six different domains, each with two signal transmitters.
http://arxiv.org/abs/1903.05392
Optimal Power Flow (OPF) can be modeled as a non-convex Quadratically Constrained Quadratic Program (QCQP). Our purpose is to solve OPF to global optimality. To this end, we specialize the Mixed-Integer Quadratic Convex Reformulation method (MIQCR) to (OPF). This is a method in two steps. First, a Semi-Definite Programming (SDP) relaxation of (OPF) is solved. Then the optimal dual variables of this relaxation are used to reformulate OPF into an equivalent new quadratic program, where all the non-convexity is moved to one additional constraint. In the second step, this reformulation is solved within a branch-and-bound algorithm, where at each node a quadratic and convex relaxation of the reformulated problem, obtained by relaxing the non-convex added constraint, is solved. The key point of our approach is that the lower bound at the root node of the branch-and-bound tree is equal to the SDP relaxation value. We test this method on several OPF cases, from two-bus networks to more-than-a-thousand-buses networks from the MAT-POWER repository. Our first results are very encouraging.
http://arxiv.org/abs/1903.05390
The Extended Kalman Filter (EKF) is both the historical algorithm for multi-sensor fusion and still state of the art in numerous industrial applications. However, it may prove inconsistent in the presence of unobservability under a group of transformations. In this paper we first build an alternative EKF based on an alternative nonlinear state error. This EKF is intimately related to the theory of the Invariant EKF (IEKF). Then, under a simple compatibility assumption between the error and the transformation group, we prove the linearized model of the alternative EKF automatically captures the unobservable directions, and many desirable properties of the linear case then directly follow. This provides a novel fundamental result in filtering theory. We apply the theory to multi-sensor fusion for navigation, when all the sensors are attached to the vehicle and do not have access to absolute information, as typically occurs in GPS-denied environments. In the context of Simultaneous Localization And Mapping (SLAM), Monte-Carlo runs and comparisons to OC-EKF, robocentric EKF, and optimization-based smoothing algorithms (iSAM) illustrate the results. The proposed EKF is also proved to outperform standard EKF and to achieve comparable performance to iSAM on a publicly available real dataset for multi-robot SLAM.
http://arxiv.org/abs/1903.05384
In real-world machine learning applications, there is a cost associated with sampling of different features. Budgeted learning can be used to select which feature-values to acquire from each instance in a dataset, such that the best model is induced under a given constraint. However, this approach is not possible in the domain of online learning since one may not retroactively acquire feature-values from past instances. In online learning, the challenge is to find the optimum set of features to be acquired from each instance upon arrival from a data stream. In this paper we introduce the issue of online budgeted learning and describe a general framework for addressing this challenge. We propose two types of feature value acquisition policies based on the multi-armed bandit problem: random and adaptive. Adaptive policies perform online adjustments according to new information coming from a data stream, while random policies are not sensitive to the information that arrives from the data stream. Our comparative study on five real-world datasets indicates that adaptive policies outperform random policies for most budget limitations and datasets. Furthermore, we found that in some cases adaptive policies achieve near-optimal results.
http://arxiv.org/abs/1903.05382
Training semantic parsers from weak supervision (denotations) rather than strong supervision (programs) complicates training in two ways. First, a large search space of potential programs needs to be explored at training time to find a correct program. Second, spurious programs that accidentally lead to a correct denotation add noise to training. In this work we propose that in closed worlds with clear semantic types, one can substantially alleviate these problems by utilizing an abstract representation, where tokens in both the language utterance and program are lifted to an abstract form. We show that these abstractions can be defined with a handful of lexical rules and that they result in sharing between different examples that alleviates the difficulties in training. To test our approach, we develop the first semantic parser for CNLVR, a challenging visual reasoning dataset, where the search space is large and overcoming spuriousness is critical, because denotations are either TRUE or FALSE, and thus random programs are likely to lead to a correct denotation. Our method substantially improves performance, and reaches 82.5% accuracy, a 14.7% absolute accuracy improvement compared to the best reported accuracy so far.
http://arxiv.org/abs/1711.05240
Face liveness detection is an essential prerequisite for face recognition applications. Previous face liveness detection methods usually train a binary classifier to differentiate between a fake face and a real face before face recognition. The client identity information is not utilized in previous face liveness detection methods. However, in practical face recognition applications, face spoofing attacks are always aimed at a specific client, and the client identity information can provide useful clues for face liveness detection. In this paper, we propose a face liveness detection method based on the client identity using Siamese network. We detect face liveness after face recognition instead of before face recognition, that is, we detect face liveness with the client identity information. We train a Siamese network with image pairs. Each image pair consists of two real face images or one real and one fake face images. The face images in each pair come from a same client. Given a test face image, the face image is firstly recognized by face recognition system, then the real face image of the identified client is retrieved to help the face liveness detection. Experiment results demonstrate the effectiveness of our method.
http://arxiv.org/abs/1903.05369
Experience-based planning domains have been proposed to improve problem solving by learning from experience. They rely on acquiring and using task knowledge, i.e., activity schemata, for generating solutions to problem instances in a class of tasks. Using Three-Valued Logic Analysis (TVLA), we extend previous work to generate a set of conditions that determine the scope of applicability of an activity schema. The inferred scope is a bounded representation of a set of problems of potentially unbounded size, in the form of a 3-valued logical structure, which is used to automatically find an applicable activity schema for solving task problems. We validate this work in two classical planning domains.
http://arxiv.org/abs/1903.06015
Future mobile devices are anticipated to perceive, understand and react to the world on their own by running multiple correlated deep neural networks on-device. Yet the complexity of these neural networks needs to be trimmed down both within-model and cross-model to fit in mobile storage and memory. Previous studies focus on squeezing the redundancy within a single neural network. In this work, we aim to reduce the redundancy across multiple models. We propose Multi-Task Zipping (MTZ), a framework to automatically merge correlated, pre-trained deep neural networks for cross-model compression. Central in MTZ is a layer-wise neuron sharing and incoming weight updating scheme that induces a minimal change in the error function. MTZ inherits information from each model and demands light retraining to re-boost the accuracy of individual tasks. Evaluations show that MTZ is able to fully merge the hidden layers of two VGG-16 networks with a 3.18% increase in the test error averaged on ImageNet and CelebA, or share 39.61% parameters between the two networks with <0.5% increase in the test errors for both tasks. The number of iterations to retrain the combined network is at least 17.8 times lower than that of training a single VGG-16 network. Moreover, experiments show that MTZ is also able to effectively merge multiple residual networks.
http://arxiv.org/abs/1805.09791
Human Activity Recognition (HAR) using deep neural network has become a hot topic in human-computer interaction. Machine can effectively identify human naturalistic activities by learning from a large collection of sensor data. Activity recognition is not only an interesting research problem, but also has many real-world practical applications. Based on the success of residual networks in achieving a high level of aesthetic representation of the automatic learning, we propose a novel \textbf{D}ual \textbf{R}esidual \textbf{N}etwork, named DRN. DRN is implemented using two identical path frameworks consisting of (1) a short time window, which is used to capture spatial features, and (2) a long time window, which is used to capture fine temporal features. The long time window path can be made very lightweight by reducing its channel capacity, yet still being able to learn useful temporal representations for activity recognition. In this paper, we mainly focus on proposing a new model to improve the accuracy of HAR. In order to demonstrate the effectiveness of DRN model, we carried out extensive experiments and compared with conventional recognition methods (HC, CBH, CBS) and learning-based methods (AE, MLP, CNN, LSTM, Hybrid, ResNet). The benchmark datasets (OPPORTUNITY, UniMiB-SHAR) were adopted by our experiments. Results from our experiments show that our model is effective in recognizing human activities via wearable datasets. We discuss the influence of networks parameters on performance to provide insights about its optimization.
http://arxiv.org/abs/1903.05359
Accurate segmenting nuclei instances is a crucial step in computer-aided image analysis to extract rich features for cellular estimation and following diagnosis as well as treatment. While it still remains challenging because the wide existence of nuclei clusters, along with the large morphological variances among different organs make nuclei instance segmentation susceptible to over-/under-segmentation. Additionally, the inevitably subjective annotating and mislabeling prevent the network learning from reliable samples and eventually reduce the generalization capability for robustly segmenting unseen organ nuclei. To address these issues, we propose a novel deep neural network, namely Contour-aware Informative Aggregation Network (CIA-Net) with multi-level information aggregation module between two task-specific decoders. Rather than independent decoders, it leverages the merit of spatial and texture dependencies between nuclei and contour by bi-directionally aggregating task-specific features. Furthermore, we proposed a novel smooth truncated loss that modulates losses to reduce the perturbation from outliers. Consequently, the network can focus on learning from reliable and informative samples, which inherently improves the generalization capability. Experiments on the 2018 MICCAI challenge of Multi-Organ-Nuclei-Segmentation validated the effectiveness of our proposed method, surpassing all the other 35 competitive teams by a significant margin.
http://arxiv.org/abs/1903.05358
Learning the dynamics of robots from data can help achieve more accurate tracking controllers, or aid their navigation algorithms. However, when the actual dynamics of the robots change due to external conditions, on-line adaptation of their models is required to maintain high fidelity performance. In this work, a framework for on-line learning of robot dynamics is developed to adapt to such changes. The proposed framework employs an incremental support vector regression method to learn the model sequentially from data streams. In combination with the incremental learning, strategies for including and forgetting data are developed to obtain better generalization over the whole state space. The framework is tested in simulation and real experimental scenarios demonstrating its adaptation capabilities to changes in the robot’s dynamics.
http://arxiv.org/abs/1903.05355
Our languages are in constant flux driven by external factors such as cultural, societal and technological changes, as well as by only partially understood internal motivations. Words acquire new meanings and lose old senses, new words are coined or borrowed from other languages and obsolete words slide into obscurity. Understanding the characteristics of shifts in the meaning and in the use of words is useful for those who work with the content of historical texts, the interested general public, but also in and of itself. The findings from automatic lexical semantic change detection, and the models of diachronic conceptual change are currently being incorporated in approaches for measuring document across-time similarity, information retrieval from long-term document archives, the design of OCR algorithms, and so on. In recent years we have seen a surge in interest in the academic community in computational methods and tools supporting inquiry into diachronic conceptual change and lexical replacement. This article is an extract of a survey of recent computational techniques to tackle lexical semantic change currently under review. In this article we focus on diachronic conceptual change as an extension of semantic change.
http://arxiv.org/abs/1811.06278
Conditional generative adversarial networks (cGAN) have led to large improvements in the task of conditional image generation, which lies at the heart of computer vision. The major focus so far has been on performance improvement, while there has been little effort in making cGAN more robust to noise. The regression (of the generator) might lead to arbitrarily large errors in the output, which makes cGAN unreliable for real-world applications. In this work, we introduce a novel conditional GAN model, called RoCGAN, which leverages structure in the target space of the model to address the issue. Our model augments the generator with an unsupervised pathway, which promotes the outputs of the generator to span the target manifold even in the presence of intense noise. We prove that RoCGAN share similar theoretical properties as GAN and experimentally verify that our model outperforms existing state-of-the-art cGAN architectures by a large margin in a variety of domains including images from natural scenes and faces.
http://arxiv.org/abs/1805.08657
Most NLP and Computer Vision tasks are limited to scarcity of labelled data. In social media emotion classification and other related tasks, hashtags have been used as indicators to label data. With the rapid increase in emoji usage of social media, emojis are used as an additional feature for major social NLP tasks. However, this is less explored in case of multimedia posts on social media where posts are composed of both image and text. At the same time, w.e have seen a surge in the interest to incorporate domain knowledge to improve machine understanding of text. In this paper, we investigate whether domain knowledge for emoji can improve the accuracy of emotion classification task. We exploit the importance of different modalities from social media post for emotion classification task using state-of-the-art deep learning architectures. Our experiments demonstrate that the three modalities (text, emoji and images) encode different information to express emotion and therefore can complement each other. Our results also demonstrate that emoji sense depends on the textual context, and emoji combined with text encodes better information than considered separately. The highest accuracy of 71.98\% is achieved with a training data of 550k posts.
http://arxiv.org/abs/1903.12520
We study the fabric spreading and cutting problem in apparel factories. For the sake of saving the material costs, the cutting requirement should be met exactly without producing additional garment components. For reducing the production costs, the number of lays that corresponds to the frequency of using the cutting beds should be minimized. We propose an iterated greedy algorithm for solving the fabric spreading and cutting problem. This algorithm contains a constructive procedure and an improving loop. Firstly the constructive procedure creates a set of lays in sequence, and then the improving loop tries to pick each lay from the lay set and rearrange the remaining lays into a smaller lay set. The improving loop will run until it cannot obtain any small lay set or the time limit is due. The experiment results on 500 cases shows that the proposed algorithm is effective and efficient.
http://arxiv.org/abs/1903.07557