Mutual calibration between color and depth cameras is a challenging topic in multi-modal data registration. In this paper, we are confronted with a “Bimodal Stereo” problem, which aims to solve camera pose from a pair of an uncalibrated color image and a depth map from different views automatically. To address this problem, an iterative Shape-from-Shading (SfS) based framework is proposed to estimate shape and pose simultaneously. In the pipeline, the estimated shape is refined by the shape prior from the given depth map under the estimated pose. Meanwhile, the estimated pose is improved by the registration of estimated shape and shape from given depth map. We also introduce a shading based refinement in the pipeline to address noisy depth map with holes. Extensive experiments showed that through our method, both the depth map, the recovered shape as well as its pose can be desirably refined and recovered.
http://arxiv.org/abs/1905.06499
Most existing channel pruning methods formulate the pruning task from a perspective of inefficiency reduction which iteratively rank and remove the least important filters, or find the set of filters that minimizes some reconstruction errors after pruning. In this work, we investigate the channel pruning from a new perspective with statistical modeling. We hypothesize that the number of filters at a certain layer reflects the level of ‘redundancy’ in that layer and thus formulate the pruning problem from the aspect of redundancy reduction. Based on both theoretic analysis and empirical studies, we make an important discovery: randomly pruning filters from layers of high redundancy outperforms pruning the least important filters across all layers based on the state-of-the-art ranking criterion. These results advance our understanding of pruning and further testify to the recent findings that the structure of the pruned model plays a key role in the network efficiency as compared to inherited weights.
http://arxiv.org/abs/1905.06498
This paper considers a class of rotary-wing aerial robots with unaligned propellers. By studying the dynamics of these vehicles, we show that the position and heading angle remain flat outputs of the system (similar to conventional quadrotors). The implication is that they can be commanded to follow desired trajectory setpoints in 3D space. We propose a numerical strategy based on the collocation method to facilitate the trajectory generation. This enables convenient computation of the nominal robot’s attitude and control inputs. The proposed methods are numerically verified for three multirotor robots with different dynamics. These include a tricopter with a tilting propeller, and a quadrotor and a hexacopter with unparalleled propellers.
http://arxiv.org/abs/1905.06496
Recently, semi-supervised learning methods based on generative adversarial networks (GANs) have received much attention. Among them, two distinct approaches have achieved competitive results on a variety of benchmark datasets. Bad GAN learns a classifier with unrealistic samples distributed on the complement of the support of the input data. Conversely, Triple GAN consists of a three-player game that tries to leverage good generated samples to boost classification results. In this paper, we perform a comprehensive comparison of these two approaches on different benchmark datasets. We demonstrate their different properties on image generation, and sensitivity to the amount of labeled data provided. By comprehensively comparing these two methods, we hope to shed light on the future of GAN-based semi-supervised learning.
http://arxiv.org/abs/1905.06484
We synthesize shared control protocols subject to probabilistic temporal logic specifications. More specifically, we develop a framework in which a human and an autonomy protocol can issue commands to carry out a certain task. We blend these commands into a joint input to a robot. We model the interaction between the human and the robot as a Markov decision process (MDP) that represents the shared control scenario. Using inverse reinforcement learning, we obtain an abstraction of the human’s behavior and decisions. We use randomized strategies to account for randomness in human’s decisions, caused by factors such as complexity of the task specifications or imperfect interfaces. We design the autonomy protocol to ensure that the resulting robot behavior satisfies given safety and performance specifications in probabilistic temporal logic. Additionally, the resulting strategies generate behavior as similar to the behavior induced by the human’s commands as possible. We solve the underlying problem efficiently using quasiconvex programming. Case studies involving autonomous wheelchair navigation and unmanned aerial vehicle mission planning showcase the applicability of our approach.
http://arxiv.org/abs/1905.06471
A relaxed two dimensional principal component analysis (R2DPCA) approach is proposed for face recognition. Different to the 2DPCA, 2DPCA-$L_1$ and G2DPCA, the R2DPCA utilizes the label information (if known) of training samples to calculate a relaxation vector and presents a weight to each subset of training data. A new relaxed scatter matrix is defined and the computed projection axes are able to increase the accuracy of face recognition. The optimal $L_p$-norms are selected in a reasonable range. Numerical experiments on practical face databased indicate that the R2DPCA has high generalization ability and can achieve a higher recognition rate than state-of-the-art methods.
http://arxiv.org/abs/1905.06458
Comparative graph and network analysis play an important role in both systems biology and pattern recognition, but existing surveys on the topic have historically ignored or underserved one or the other of these fields. We present an integrative introduction to the key objectives and methods of graph and network comparison in each field, with the intent of remaining accessible to relative novices in order to mitigate the barrier to interdisciplinary idea crossover. To guide our investigation, and to quantitatively justify our assertions about what the key objectives and methods of each field are, we have constructed a citation network containing 5,793 vertices from the full reference lists of over two hundred relevant papers, which we collected by searching Google Scholar for ten different network comparison-related search terms. We investigate its basic statistics and community structure, and frame our presentation around the papers found to have high importance according to five different standard centrality measures.
http://arxiv.org/abs/1905.06457
Confocal laser endomicroscopy (CLE) allow on-the-fly in vivo intraoperative imaging in a discreet field of view, especially for brain tumors, rather than extracting tissue for examination ex vivo with conventional light microscopy. Fluorescein sodium-driven CLE imaging is more interactive, rapid, and portable than conventional hematoxylin and eosin (H&E)-staining. However, it has several limitations: CLE images may be contaminated with artifacts (motion, red blood cells, noise), and neuropathologists are mainly trained on colorful stained histology slides like H&E while the CLE images are gray. To improve the diagnostic quality of CLE, we used a micrograph of an H&E slide from a glioma tumor biopsy and image style transfer, a neural network method for integrating the content and style of two images. This was done through minimizing the deviation of the target image from both the content (CLE) and style (H&E) images. The style transferred images were assessed and compared to conventional H&E histology by neurosurgeons and a neuropathologist who then validated the quality enhancement in 100 pairs of original and transformed images. Average reviewers’ score on test images showed 84 out of 100 transformed images had fewer artifacts and more noticeable critical structures compared to their original CLE form. By providing images that are more interpretable than the original CLE images and more rapidly acquired than H&E slides, the style transfer method allows a real-time, cellular-level tissue examination using CLE technology that closely resembles the conventional appearance of H&E staining and may yield better diagnostic recognition than original CLE grayscale images.
http://arxiv.org/abs/1905.06442
Existing methods for reducing the computational burden of neural networks at run-time, such as parameter pruning or dynamic computational path selection, focus solely on improving computational efficiency during inference. On the other hand, in this work, we propose a novel method which reduces the memory footprint and number of computing operations required for training and inference. Our framework efficiently integrates pruning as part of the training procedure by exploring and tracking the relative importance of convolutional channels. At each training step, we select only a subset of highly salient channels to execute according to the combinatorial upper confidence bound algorithm, and run a forward and backward pass only on these activated channels, hence learning their parameters. Consequently, we enable the efficient discovery of compact models. We validate our approach empirically on state-of-the-art CNNs - VGGNet, ResNet and DenseNet, and on several image classification datasets. Results demonstrate our framework for dynamic channel execution reduces computational cost up to 4x and parameter count up to 9x, thus reducing the memory and computational demands for discovering and training compact neural network models.
http://arxiv.org/abs/1905.06435
Humans achieve efficient learning by relying on prior knowledge about the structure of naturally occurring tasks. There has been considerable interest in designing reinforcement learning algorithms with similar properties. This includes several proposals to learn the learning algorithm itself, an idea also referred to as meta learning. One formal interpretation of this idea is in terms of a partially observable multi-task reinforcement learning problem in which information about the task is hidden from the agent. Although agents that solve partially observable environments can be trained from rewards alone, shaping an agent’s memory with additional supervision has been shown to boost learning efficiency. It is thus natural to ask what kind of supervision, if any, facilitates meta-learning. Here we explore several choices and develop an architecture that separates learning of the belief about the unknown task from learning of the policy, and that can be used effectively with privileged information about the task during training. We show that this approach can be very effective at solving standard meta-RL environments, as well as a complex continuous control environment in which a simulated robot has to execute various movement sequences.
http://arxiv.org/abs/1905.06424
One key task of fine-grained sentiment analysis on reviews is to extract aspects or features that users have expressed opinions on. This paper focuses on supervised aspect extraction using a modified CNN called controlled CNN (Ctrl). The modified CNN has two types of control modules. Through asynchronous parameter updating, it prevents over-fitting and boosts CNN’s performance significantly. This model achieves state-of-the-art results on standard aspect extraction datasets. To the best of our knowledge, this is the first paper to apply control modules to aspect extraction.
http://arxiv.org/abs/1905.06407
A fundamental concern in real-time planning is the presence of dead-ends in the state space, from which no goal is reachable. Recently, the SafeRTS algorithm was proposed for searching in such spaces. SafeRTS exploits a user-provided predicate to identify safe states, from which a goal is likely reachable, and attempts to maintain a backup plan for reaching a safe state at all times. In this paper, we study the SafeRTS approach, identify certain properties of its behavior, and design an improved framework for safe real-time search. We prove that the new approach performs at least as well as SafeRTS and present experimental results showing that its promise is fulfilled in practice.
http://arxiv.org/abs/1905.06402
Adversarial evaluation stress tests a model’s understanding of natural language. While past approaches expose superficial patterns, the resulting adversarial examples are limited in complexity and diversity. We propose human-in-the-loop adversarial generation, where human authors are guided to break models. We aid the authors with interpretations of model predictions through an interactive user interface. We apply this generation framework to a question answering task called Quizbowl, where trivia enthusiasts craft adversarial questions. The resulting questions are validated via live human–computer matches: although the questions appear ordinary to humans, they systematically stump neural and information retrieval models. The adversarial questions cover diverse phenomena from multi-hop reasoning to entity type distractors, exposing open challenges in robust question answering.
http://arxiv.org/abs/1809.02701
Benchmark data sets are an indispensable ingredient of the evaluation of graph-based machine learning methods. We release a new data set, compiled from International Planning Competitions (IPC), for benchmarking graph classification, regression, and related tasks. Apart from the graph construction (based on AI planning problems) that is interesting in its own right, the data set possesses distinctly different characteristics from popularly used benchmarks. The data set, named IPC, consists of two self-contained versions, grounded and lifted, both including graphs of large and skewedly distributed sizes, posing substantial challenges for the computation of graph models such as graph kernels and graph neural networks. The graphs in this data set are directed and the lifted version is acyclic, offering the opportunity of benchmarking specialized models for directed (acyclic) structures. Moreover, the graph generator and the labeling are computer programmed; thus, the data set may be extended easily if a larger scale is desired. The data set is accessible from \url{https://github.com/IBM/IPC-graph-data}.
http://arxiv.org/abs/1905.06393
The relationship between two entities in a sentence is often implied by word order and common sense, rather than an explicit predicate. For example, it is evident that “Fed chair Powell indicates rate hike” implies (Powell, is a, Fed chair) and (Powell, works for, Fed). These tuples are just as significant as the explicit-predicate tuple (Powell, indicates, rate hike), but have much lower recall under traditional Open Information Extraction (OpenIE) systems. Implicit tuples are our term for this type of extraction where the relation is not present in the input sentence. There is very little OpenIE training data available relative to other NLP tasks and none focused on implicit relations. We develop an open source, parse-based tool for converting large reading comprehension datasets to OpenIE datasets and release a dataset 35x larger than previously available by sentence count. A baseline neural model trained on this data outperforms previous methods on the implicit extraction task.
http://arxiv.org/abs/1905.07471
Unmanned Aerial Vehicles (UAVs) are getting closer to becoming ubiquitous in everyday life. Among them, Micro Aerial Vehicles (MAVs) have seen an outburst of attention recently, specifically in the area with a demand for autonomy. A key challenge standing in the way of making MAVs autonomous is that researchers lack the comprehensive understanding of how performance, power, and computational bottlenecks affect MAV applications. MAVs must operate under a stringent power budget, which severely limits their flight endurance time. As such, there is a need for new tools, benchmarks, and methodologies to foster the systematic development of autonomous MAVs. In this paper, we introduce the `MAVBench’ framework which consists of a closed-loop simulator and an end-to-end application benchmark suite. A closed-loop simulation platform is needed to probe and understand the intra-system (application data flow) and inter-system (system and environment) interactions in MAV applications to pinpoint bottlenecks and identify opportunities for hardware and software co-design and optimization. In addition to the simulator, MAVBench provides a benchmark suite, the first of its kind, consisting of a variety of MAV applications designed to enable computer architects to perform characterization and develop future aerial computing systems. Using our open source, end-to-end experimental platform, we uncover a hidden, and thus far unexpected compute to total system energy relationship in MAVs. Furthermore, we explore the role of compute by presenting three case studies targeting performance, energy and reliability. These studies confirm that an efficient system design can improve MAV’s battery consumption by up to 1.8X.
http://arxiv.org/abs/1905.06388
In this paper, we propose to combine detections from background subtraction and from a multiclass object detector for multiple object tracking (MOT) in urban traffic scenes. These objects are associated across frames using spatial, colour and class label information, and trajectory prediction is evaluated to yield the final MOT outputs. The proposed method was tested on the Urban tracker dataset and shows competitive performances compared to state-of-the-art approaches. Results show that the integration of different detection inputs remains a challenging task that greatly affects the MOT performance.
http://arxiv.org/abs/1905.06381
Elimination is a word puzzle game for browsers and mobile devices, where all levels are generated by a constrained evolutionary algorithm with no human intervention. This paper describes the design of the game and its level generation methods, and analysis of playtraces from almost a thousand users who played the game since its release. The analysis corroborates that the level generator creates a sawtooth-shaped difficulty curve, as intended. The analysis also offers insights into player behavior in this game.
http://arxiv.org/abs/1905.06379
Planning has been very successful for control tasks with known environment dynamics. To leverage planning in unknown environments, the agent needs to learn the dynamics from interactions with the world. However, learning dynamics models that are accurate enough for planning has been a long-standing challenge, especially in image-based domains. We propose the Deep Planning Network (PlaNet), a purely model-based agent that learns the environment dynamics from images and chooses actions through fast online planning in latent space. To achieve high performance, the dynamics model must accurately predict the rewards ahead for multiple time steps. We approach this using a latent dynamics model with both deterministic and stochastic transition components. Moreover, we propose a multi-step variational inference objective that we name latent overshooting. Using only pixel observations, our agent solves continuous control tasks with contact dynamics, partial observability, and sparse rewards, which exceed the difficulty of tasks that were previously solved by planning with learned models. PlaNet uses substantially fewer episodes and reaches final performance close to and sometimes higher than strong model-free algorithms.
http://arxiv.org/abs/1811.04551
This paper develops a novel approach for high dynamic-range compression. It relies on the widely accepted assumption that the human visual system is not very sensitive to absolute luminance reaching the retina, but rather responds to relative luminance ratios. Dynamic-range compression is then formulated as a regularized optimization in which the image dynamic range is reduced while the local contrast of the original scene is preserved. Our method is shown to be capable of drastic dynamic-range compression, while preserving fine details and avoiding common artifacts such as halos, gradient reversals, or loss of local contrast.
http://arxiv.org/abs/1905.06372
Segmentation of ultra-high resolution images is increasingly demanded, yet poses significant challenges for algorithm efficiency, in particular considering the (GPU) memory limits. Current approaches either downsample an ultra-high resolution image or crop it into small patches for separate processing. In either way, the loss of local fine details or global contextual information results in limited segmentation accuracy. We propose collaborative Global-Local Networks (GLNet) to effectively preserve both global and local information in a highly memory-efficient manner. GLNet is composed of a global branch and a local branch, taking the downsampled entire image and its cropped local patches as respective inputs. For segmentation, GLNet deeply fuses feature maps from two branches, capturing both the high-resolution fine structures from zoomed-in local patches and the contextual dependency from the downsampled input. To further resolve the potential class imbalance problem between background and foreground regions, we present a coarse-to-fine variant of GLNet, also being memory-efficient. Extensive experiments and analyses have been performed on three real-world ultra-high aerial and medical image datasets (resolution up to 30 million pixels). With only one single 1080Ti GPU and less than 2GB memory used, our GLNet yields high-quality segmentation results and achieves much more competitive accuracy-memory usage trade-offs compared to state-of-the-arts.
http://arxiv.org/abs/1905.06368
Chest X-ray (CXR) is the most common X-ray examination performed in daily clinical practice for the diagnosis of various heart and lung abnormalities. The large amount of data to be read and reported, with 100+ studies per day for a single radiologist, poses a challenge in maintaining consistently high interpretation accuracy. In this work, we propose a method for the classification of different abnormalities based on CXR scans of the human body. The system is based on a novel multi-task deep learning architecture that in addition to the abnormality classification, supports the segmentation of the lungs and heart and classification of regions where the abnormality is located. We demonstrate that by training these tasks concurrently, one can increase the classification performance of the model. Experiments were performed on an extensive collection of 297,541 chest X-ray images from 86,876 patients, leading to a state-of-the-art performance level of 0.883 AUC on average for 12 different abnormalities. We also conducted a detailed performance analysis and compared the accuracy of our system with 3 board-certified radiologists. In this context, we highlight the high level of label noise inherent to this problem. On a reduced subset containing only cases with high confidence reference labels based on the consensus of the 3 radiologists, our system reached an average AUC of 0.945.
http://arxiv.org/abs/1905.06362
We propose a novel method of deep spatial matching (DSM) for image retrieval. Initial ranking is based on image descriptors extracted from convolutional neural network activations by global pooling, as in recent state-of-the-art work. However, the same sparse 3D activation tensor is also approximated by a collection of local features. These local features are then robustly matched to approximate the optimal alignment of the tensors. This happens without any network modification, additional layers or training. No local feature detection happens on the original image. No local feature descriptors and no visual vocabulary are needed throughout the whole process. We experimentally show that the proposed method achieves the state-of-the-art performance on standard benchmarks across different network architectures and different global pooling methods. The highest gain in performance is achieved when diffusion on the nearest-neighbor graph of global descriptors is initiated from spatially verified images.
http://arxiv.org/abs/1905.06358
In cinema, large camera lenses create beautiful shallow depth of field (DOF), but make focusing difficult and expensive. Accurate cinema focus usually relies on a script and a person to control focus in realtime. Casual videographers often crave cinematic focus, but fail to achieve it. We either sacrifice shallow DOF, as in smartphone videos; or we struggle to deliver accurate focus, as in videos from larger cameras. This paper is about a new approach in the pursuit of cinematic focus for casual videography. We present a system that synthetically renders refocusable video from a deep DOF video shot with a smartphone, and analyzes future video frames to deliver context-aware autofocus for the current frame. To create refocusable video, we extend recent machine learning methods designed for still photography, contributing a new dataset for machine training, a rendering model better suited to cinema focus, and a filtering solution for temporal coherence. To choose focus accurately for each frame, we demonstrate autofocus that looks at upcoming video frames and applies AI-assist modules such as motion, face, audio and saliency detection. We also show that autofocus benefits from machine learning and a large-scale video dataset with focus annotation, where we use our RVR-LAAF GUI to create this sizable dataset efficiently. We deliver, for example, a shallow DOF video where the autofocus transitions onto each person before she begins to speak. This is impossible for conventional camera autofocus because it would require seeing into the future.
http://arxiv.org/abs/1905.06326
Many common character-level, string-to-string transduction tasks, e.g., grapheme-to-phoneme conversion and morphological inflection, consist almost exclusively of monotonic transduction. Neural sequence-to-sequence models with soft attention, non-monotonic models, outperform popular monotonic models. In this work, we ask the following question: Is monotonicity really a helpful inductive bias in these tasks? We develop a hard attention sequence-to-sequence model that enforces strict monotonicity and learns alignment jointly. With the help of dynamic programming, we are able to compute the exact marginalization over all alignments. Our models achieve state-of-the-art performance on morphological inflection. Furthermore, we find strong performance on two other character-level transduction tasks.
http://arxiv.org/abs/1905.06319
Contextualized representation models such as ELMo (Peters et al., 2018a) and BERT (Devlin et al., 2018) have recently achieved state-of-the-art results on a diverse array of downstream NLP tasks. Building on recent token-level probing work, we introduce a novel edge probing task design and construct a broad suite of sub-sentence tasks derived from the traditional structured NLP pipeline. We probe word-level contextual representations from four recent models and investigate how they encode sentence structure across a range of syntactic, semantic, local, and long-range phenomena. We find that existing models trained on language modeling and translation produce strong representations for syntactic phenomena, but only offer comparably small improvements on semantic tasks over a non-contextual baseline.
http://arxiv.org/abs/1905.06316
Diabetic retinopathy (DR) is a common retinal disease that leads to blindness. For diagnosis purposes, DR image grading aims to provide automatic DR grade classification, which is not addressed in conventional research methods of binary DR image classification. Small objects in the eye images, like lesions and microaneurysms, are essential to DR grading in medical imaging, but they could easily be influenced by other objects. To address these challenges, we propose a new deep learning architecture, called BiRA-Net, which combines the attention model for feature extraction and bilinear model for fine-grained classification. Furthermore, in considering the distance between different grades of different DR categories, we propose a new loss function, called grading loss, which leads to improved training convergence of the proposed approach. Experimental results are provided to demonstrate the superior performance of the proposed approach.
http://arxiv.org/abs/1905.06312
Simultaneous Localization and Mapping (SLAM) is the problem of constructing a map of a mobile agent’s environment while localizing the agent within the map. Dense SLAM algorithms perform reconstruction and localization at pixel granularity. These algorithms require a lot of computational power, which has hindered their use on low-power resource-constrained devices. Approximate computing can be used to speed up SLAM implementations as long as the approximations do not prevent the agent from navigating correctly through the environment. Previous studies of approximation in SLAM have assumed that the entire trajectory of the agent is known before the agent starts, and they have focused on offline controllers that set approximation knobs at the start of the trajectory. In practice, the trajectory is not known ahead of time, and allowing knob settings to change dynamically opens up more opportunities for reducing computation time and energy. We describe SLAMBooster, an application-aware, online control system for dense SLAM that adaptively controls approximation knobs during the motion of the agent. SLAMBooster is based on a control technique called proportional-integral-derivative (PID) controller but our experiments showed this application-agnostic controller led to an unacceptable reduction in localization accuracy. To address this problem, SLAMBooster also exploits domain knowledge for controlling approximation by performing smooth surface detection and pose correction. We implemented SLAMBooster in the open-source SLAMBench framework and evaluated it on several trajectories. Our experiments show that on the average, SLAMBooster reduces the computation time by 72% and energy consumption by 35% on an embedded platform, while maintaining the accuracy of localization within reasonable bounds. These improvements make it feasible to deploy SLAM on a wider range of devices.
http://arxiv.org/abs/1811.01516
This paper deals with the convergence time analysis of a class of fixed-time stable systems with the aim to provide a new non-conservative upper bound for its settling time. Our contribution is fourfold. First, we revisit the well-known class of fixed-time stable systems, given in (Polyakov et al.,2012}, while showing the conservatism of the classical upper estimate of the settling time. Second, we provide the smallest constant that uniformly upper bounds the settling time of any trajectory of the system under consideration. Third, introducing a slight modification of the previous class of fixed-time systems, we propose a new predefined-time convergent algorithm where the least upper bound of the settling time is set a priori as a parameter of the system. At last, predefined-time controllers for first order and second order systems are introduced. Some simulation results highlight the performance of the proposed scheme in terms of settling time estimation compared to existing methods.
http://arxiv.org/abs/1809.07012
The Internet and, in particular, Online Social Networks have changed the way that terrorist and extremist groups can influence and radicalise individuals. Recent reports show that the mode of operation of these groups starts by exposing a wide audience to extremist material online, before migrating them to less open online platforms for further radicalization. Thus, identifying radical content online is crucial to limit the reach and spread of the extremist narrative. In this paper, our aim is to identify measures to automatically detect radical content in social media. We identify several signals, including textual, psychological and behavioural, that together allow for the classification of radical messages. Our contribution is three-fold: (1) we analyze propaganda material published by extremist groups and create a contextual text-based model of radical content, (2) we build a model of psychological properties inferred from these material, and (3) we evaluate these models on Twitter to determine the extent to which it is possible to automatically identify online radical tweets. Our results show that radical users do exhibit distinguishable textual, psychological, and behavioural properties. We find that the psychological properties are among the most distinguishing features. Additionally, our results show that textual models using vector embedding features significantly improves the detection over TF-IDF features. We validate our approach on two experiments achieving high accuracy. Our findings can be utilized as signals for detecting online radicalization activities.
http://arxiv.org/abs/1905.08067
In this paper, we propose a novel generative adversarial network (GAN) for 3D point clouds generation, which is called tree-GAN. To achieve state-of-the-art performance for multi-class 3D point cloud generation, a tree-structured graph convolution network (TreeGCN) is introduced as a generator for tree-GAN. Because TreeGCN performs graph convolutions within a tree, it can use ancestor information to boost the representation power for features. To evaluate GANs for 3D point clouds accurately, we develop a novel evaluation metric called Frechet point cloud distance (FPD). Experimental results demonstrate that the proposed tree-GAN outperforms state-of-the-art GANs in terms of both conventional metrics and FPD, and can generate point clouds for different semantic parts without prior knowledge.
http://arxiv.org/abs/1905.06292
The Winograd Schema Challenge (WSC) dataset WSC273 and its inference counterpart WNLI are popular benchmarks for natural language understanding and commonsense reasoning. In this paper, we show that the performance of three language models on WSC273 strongly improves when fine-tuned on a similar pronoun disambiguation problem dataset (denoted WSCR). We additionally generate a large unsupervised WSC-like dataset. By fine-tuning the BERT language model both on the introduced and on the WSCR dataset, we achieve overall accuracies of 72.2% and 71.9% on WSC273 and WNLI, improving the previous state-of-the-art solutions by 8.5% and 6.8%, respectively. Furthermore, our fine-tuned models are also consistently more robust on the “complex” subsets of WSC273, introduced by Trichelair et al. (2018).
http://arxiv.org/abs/1905.06290
The interactive machine learning (IML) community aims to augment humans’ ability to learn and make decisions over time through the development of automated decision-making systems. This interaction represents a collaboration between multiple intelligent systems—humans and machines. A lack of appropriate consideration for the humans involved can lead to problematic system behaviour, and issues of fairness, accountability, and transparency. This work presents a human-centred thinking approach to applying IML methods. This guide is intended to be used by AI practitioners who incorporate human factors in their work. These practitioners are responsible for the health, safety, and well-being of interacting humans. An obligation of responsibility for public interaction means acting with integrity, honesty, fairness, and abiding by applicable legal statutes. With these values and principles in mind, we as a research community can better achieve the collective goal of augmenting human ability. This practical guide aims to support many of the responsible decisions necessary throughout iterative design, development, and dissemination of IML systems.
http://arxiv.org/abs/1905.06289
We apply ideas from abstract argumentation theory to study cooperative game theory. Building on Dung’s results in his seminal paper, we further the correspondence between Dung’s four argumentation semantics and solution concepts in cooperative game theory by showing that complete extensions (the grounded extension) correspond to Roth’s subsolutions (respectively, the supercore). We then investigate the relationship between well-founded argumentation frameworks and convex games, where in each case the semantics (respectively, solution concepts) coincide; we prove that three-player convex games do not in general have well-founded argumentation frameworks.
http://arxiv.org/abs/1905.10922
Colon Cancer is one of the most common types of cancer. The treatment is planned to depend on the grade or stage of cancer. One of the preconditions for grading of colon cancer is to segment the glandular structures of tissues. Manual segmentation method is very time-consuming, and it leads to life risk for the patients. The principal objective of this project is to assist the pathologist to accurate detection of colon cancer. In this paper, the authors have proposed an algorithm for an automatic segmentation of glands in colon histology using local intensity and texture features. Here the dataset images are cropped into patches with different window sizes and taken the intensity of those patches, and also calculated texture-based features. Random forest classifier has been used to classify this patch into different labels. A multilevel random forest technique in a hierarchical way is proposed. This solution is fast, accurate and it is very much applicable in a clinical setup.
http://arxiv.org/abs/1905.08611
The end-to-end approach for single-channel speech separation has been studied recently and shown promising results. This paper extended the previous approach and proposed a new end-to-end model for multi-channel speech separation. The primary contributions of this work include 1) an integrated waveform-in waveform-out separation system in a single neural network architecture. 2) We reformulate the traditional short time Fourier transform (STFT) and inter-channel phase difference (IPD) as a function of time-domain convolution with a special kernel. 3) We further relaxed those fixed kernels to be learnable, so that the entire architecture becomes purely data-driven and can be trained from end-to-end. We demonstrate on the WSJ0 far-field speech separation task that, with the benefit of learnable spatial features, our proposed end-to-end multi-channel model significantly improved the performance of previous end-to-end single-channel method and traditional multi-channel methods.
http://arxiv.org/abs/1905.06286
Model-free reinforcement learning based methods such as Proximal Policy Optimization, or Q-learning typically require thousands of interactions with the environment to approximate the optimum controller which may not always be feasible in robotics due to safety and time consumption. Model-based methods such as PILCO or BlackDrops, while data-efficient, provide solutions with limited robustness and complexity. To address this tradeoff, we introduce active uncertainty reduction-based virtual environments, which are formed through limited trials conducted in the original environment. We provide an efficient method for uncertainty management, which is used as a metric for self-improvement by identification of the points with maximum expected improvement through adaptive sampling. Capturing the uncertainty also allows for better mimicking of the reward responses of the original system. Our approach enables the use of complex policy structures and reward functions through a unique combination of model-based and model-free methods, while still retaining the data efficiency. We demonstrate the validity of our method on several classic reinforcement learning problems in OpenAI gym. We prove that our approach offers a better modeling capacity for complex system dynamics as compared to established methods.
http://arxiv.org/abs/1905.06274
Most work on automated deception detection (ADD) in video has two restrictions: (i) it focuses on a video of one person, and (ii) it focuses on a single act of deception in a one or two minute video. In this paper, we propose a new ADD framework which captures long term deception in a group setting. We study deception in the well-known Resistance game (like Mafia and Werewolf) which consists of 5-8 players of whom 2-3 are spies. Spies are deceptive throughout the game (typically 30-65 minutes) to keep their identity hidden. We develop an ensemble predictive model to identify spies in Resistance videos. We show that features from low-level and high-level video analysis are insufficient, but when combined with a new class of features that we call LiarRank, produce the best results. We achieve AUCs of over 0.70 in a fully automated setting. Our demo can be found at this http URL
http://arxiv.org/abs/1905.08617
We introduce SparseVM, a method to register clinical 3D scans faster and more accurately than previously possible. Deformable alignment, or registration, of clinical scans is a fundamental task for many medical image applications such as longitudinal population studies. Most registration algorithms are designed for high-resolution research-quality scans and under-perform when applied to clinical data. Clinical scans present unique challenges because, in contrast to research-quality scans, clinical scans are often sparse, missing up to 85% of the slices available in research scans. We build on a state-of-the-art learning-based registration method to improve the accuracy of sparse clinical image registration and demonstrate our method on a clinically-acquired MRI dataset of stroke patients. SparseVM registers 3D scans in under a second on a GPU, which is over 1000x faster than the most accurate clinical registration methods, without compromising accuracy. Because of this, SparseVM enables clinical analyses that were not previously possible. The code is publicly available at voxelmorph.mit.edu.
http://arxiv.org/abs/1812.06932
Designing neural networks for object recognition requires considerable architecture engineering. As a remedy, neuro-evolutionary network architecture search, which automatically searches for optimal network architectures using evolutionary algorithms, has recently become very popular. Although very effective, evolutionary algorithms rely heavily on having a large population of individuals (i.e., network architectures) and is therefore memory expensive. In this work, we propose a Regularized Evolutionary Algorithm with low memory footprint to evolve a dynamic image classifier. In details, we introduce novel custom operators that regularize the evolutionary process of a micro-population of 10 individuals. We conduct experiments on three different digits datasets (MNIST, USPS, SVHN) and show that our evolutionary method obtains competitive results with the current state-of-the-art.
http://arxiv.org/abs/1905.06252
Machine learning and data mining techniques have been used extensively in order to detect credit card frauds. However, most studies consider credit card transactions as isolated events and not as a sequence of transactions. In this article, we model a sequence of credit card transactions from three different perspectives, namely (i) does the sequence contain a Fraud? (ii) Is the sequence obtained by fixing the card-holder or the payment terminal? (iii) Is it a sequence of spent amount or of elapsed time between the current and previous transactions? Combinations of the three binary perspectives give eight sets of sequences from the (training) set of transactions. Each one of these sets is modelled with a Hidden Markov Model (HMM). Each HMM associates a likelihood to a transaction given its sequence of previous transactions. These likelihoods are used as additional features in a Random Forest classifier for fraud detection. This multiple perspectives HMM-based approach enables an automatic feature engineering in order to model the sequential properties of the dataset with respect to the classification task. This strategy allows for a 15% increase in the precision-recall AUC compared to the state of the art feature engineering strategy for credit card fraud detection.
http://arxiv.org/abs/1905.06247
Multi-Domain Learning (MDL) refers to the problem of learning a set of models derived from a common deep architecture, each one specialized to perform a task in a certain domain (e.g., photos, sketches, paintings). This paper tackles MDL with a particular interest in obtaining domain-specific models with an adjustable budget in terms of the number of network parameters and computational complexity. Our intuition is that, as in real applications the number of domains and tasks can be very large, an effective MDL approach should not only focus on accuracy but also on having as few parameters as possible. To implement this idea we derive specialized deep models for each domain by adapting a pre-trained architecture but, differently from other methods, we propose a novel strategy to automatically adjust the computational complexity of the network. To this aim, we introduce Budget-Aware Adapters that select the most relevant feature channels to better handle data from a novel domain. Some constraints on the number of active switches are imposed in order to obtain a network respecting the desired complexity budget. Experimentally, we show that our approach leads to recognition accuracy competitive with state-of-the-art approaches but with much lighter networks both in terms of storage and computation.
http://arxiv.org/abs/1905.06242
Research on parsing language to SQL has largely ignored the structure of the database (DB) schema, either because the DB was very simple, or because it was observed at both training and test time. In \spider{}, a recently-released text-to-SQL dataset, new and complex DBs are given at test time, and so the structure of the DB schema can inform the predicted SQL query. In this paper, we present an encoder-decoder semantic parser, where the structure of the DB schema is encoded with a graph neural network, and this representation is later used at both encoding and decoding time. Evaluation shows that encoding the schema structure improves our parser accuracy from 33.8% to 39.4%, dramatically above the current state of the art, which is at 19.7%.
http://arxiv.org/abs/1905.06241
We address the task of 3D semantic scene completion, i.e. , given a single depth image, we predict the semantic labels and occupancy of voxels in a 3D grid representing the scene. In light of the recently introduced generative adversarial networks (GAN), our goal is to explore the potential of this model and the efficiency of various important design choices. Our results show that using conditional GANs outperforms the vanilla GAN setup. We evaluate these architecture designs on several datasets. Based on our experiments, we demonstrate that GANs are able to outperform the performance of a baseline 3D CNN in case of clean annotations, but they suffer from poorly aligned annotations.
http://arxiv.org/abs/1905.06231
Signed graphs encode positive (attractive) and negative (repulsive) relations between nodes. We extend spectral clustering to signed graphs via the one-parameter family of Signed Power Mean Laplacians, defined as the matrix power mean of normalized standard and signless Laplacians of positive and negative edges. We provide a thorough analysis of the proposed approach in the setting of a general Stochastic Block Model that includes models such as the Labeled Stochastic Block Model and the Censored Block Model. We show that in expectation the signed power mean Laplacian captures the ground truth clusters under reasonable settings where state-of-the-art approaches fail. Moreover, we prove that the eigenvalues and eigenvector of the signed power mean Laplacian concentrate around their expectation under reasonable conditions in the general Stochastic Block Model. Extensive experiments on random graphs and real world datasets confirm the theoretically predicted behaviour of the signed power mean Laplacian and show that it compares favourably with state-of-the-art methods.
http://arxiv.org/abs/1905.06230
Digital Image Correlation (DIC) is a powerful tool used to evaluate displacements and deformations in a non-intrusive manner. By comparing two images, one of the undeformed reference state of a specimen and another of the deformed target state, the relative displacement between those two states is determined. DIC is well known and often used for post-processing analysis of in-plane displacements and deformation of specimen. Increasing the analysis speed to enable real-time DIC analysis will be beneficial and extend the field of use of this technique. Here we tested several combinations of the most common DIC methods in combination with different parallelization approaches in MATLAB and evaluated their performance to determine whether real-time analysis is possible with these methods. To reflect improvements in computing technology different hardware settings were also analysed. We found that implementation problems can reduce the efficiency of a theoretically superior algorithm such that it becomes practically slower than a sub-optimal algorithm. The Newton-Raphson algorithm in combination with a modified Particle Swarm algorithm in parallel image computation was found to be most effective. This is contrary to theory, suggesting that the inverse-compositional Gauss-Newton algorithm is superior. As expected, the Brute Force Search algorithm is the least effective method. We also found that the correct choice of parallelization tasks is crucial to achieve improvements in computing speed. A poorly chosen parallelisation approach with high parallel overhead leads to inferior performance. Finally, irrespective of the computing mode the correct choice of combinations of integer-pixel and sub-pixel search algorithms is decisive for an efficient analysis. Using currently available hardware real-time analysis at high framerates remains an aspiration.
http://arxiv.org/abs/1905.06228
Natural Language Sentence Matching (NLSM) has gained substantial attention from both academics and the industry, and rich public datasets contribute a lot to this process. However, biased datasets can also hurt the generalization performance of trained models and give untrustworthy evaluation results. For many NLSM datasets, the providers select some pairs of sentences into the datasets, and this sampling procedure can easily bring unintended pattern, i.e., selection bias. One example is the QuoraQP dataset, where some content-independent naive features are unreasonably predictive. Such features are the reflection of the selection bias and termed as the leakage features. In this paper, we investigate the problem of selection bias on six NLSM datasets and find that four out of them are significantly biased. We further propose a training and evaluation framework to alleviate the bias. Experimental results on QuoraQP suggest that the proposed framework can improve the generalization ability of trained models, and give more trustworthy evaluation results for real-world adoptions.
http://arxiv.org/abs/1905.06221
This paper studies semi-supervised object classification in relational data, which is a fundamental problem in relational data modeling. The problem has been extensively studied in the literature of both statistical relational learning (e.g. relational Markov networks) and graph neural networks (e.g. graph convolutional networks). Statistical relational learning methods can effectively model the dependency of object labels through conditional random fields for collective classification, whereas graph neural networks learn effective object representations for classification through end-to-end training. In this paper, we propose the Graph Markov Neural Network (GMNN) that combines the advantages of both worlds. A GMNN models the joint distribution of object labels with a conditional random field, which can be effectively trained with the variational EM algorithm. In the E-step, one graph neural network learns effective object representations for approximating the posterior distributions of object labels. In the M-step, another graph neural network is used to model the local label dependency. Experiments on object classification, link classification, and unsupervised node representation learning show that GMNN achieves state-of-the-art results.
http://arxiv.org/abs/1905.06214
Inferring the 3D geometry and the semantic meaning of surfaces, which are occluded, is a very challenging task. Recently, a first end-to-end learning approach has been proposed that completes a scene from a single depth image. The approach voxelizes the scene and predicts for each voxel if it is occupied and, if it is occupied, the semantic class label. In this work, we propose a two stream approach that leverages depth information and semantic information, which is inferred from the RGB image, for this task. The approach constructs an incomplete 3D semantic tensor, which uses a compact three-channel encoding for the inferred semantic information, and uses a 3D CNN to infer the complete 3D semantic tensor. In our experimental evaluation, we show that the proposed two stream approach substantially outperforms the state-of-the-art for semantic scene completion.
http://arxiv.org/abs/1804.03550
Large knowledge bases (KBs) are useful for many AI tasks, but are difficult to integrate into modern gradient-based learning systems. Here we describe a framework for accessing soft symbolic database using only differentiable operators. For example, this framework makes it easy to conveniently write neural models that adjust confidences associated with facts in a soft KB; incorporate prior knowledge in the form of hand-coded KB access rules; or learn to instantiate query templates using information extracted from text. NQL can work well with KBs with millions of tuples and hundreds of thousands of entities on a single GPU.
http://arxiv.org/abs/1905.06209