Latest in cs.ai

total 15698took 0.12s
Revisiting Multi-Step Nonlinearity Compensation with Machine LearningApr 22 2019For the efficient compensation of fiber nonlinearity, one of the guiding principles appears to be: fewer steps are better and more efficient. We challenge this assumption and show that carefully designed multi-step approaches can lead to better performance-complexity ... More
FeatherNets: Convolutional Neural Networks as Light as Feather for Face Anti-spoofingApr 22 2019Face Anti-spoofing gains increased attentions recently in both academic and industrial fields. With the emergence of various CNN based solutions, the multi-modal(RGB, depth and IR) methods based CNN showed better performance than single modal classifiers. ... More
Obfuscation for Privacy-preserving Syntactic ParsingApr 21 2019The goal of homomorphic encryption is to encrypt data such that another party can operate on it without being explicitly exposed to the content of the original data. We introduce an idea for a privacy-preserving transformation on natural language data, ... More
Specification-Driven Predictive Business Process MonitoringApr 20 2019Predictive analysis in business process monitoring aims at forecasting the future information of a running business process. The prediction is typically made based on the model extracted from historical process execution logs (event logs). In practice, ... More
Visualizing the decision-making process in deep neural decision forestApr 19 2019Deep neural decision forest (NDF) achieved remarkable performance on various vision tasks via combining decision tree and deep representation learning. In this work, we first trace the decision-making process of this model and visualize saliency maps ... More
Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-NetApr 19 2019Segmentation of pancreas is important for medical image analysis, yet it faces great challenges of class imbalance, background distractions and non-rigid geometrical features. To address these difficulties, we introduce a Deep Q Network(DQN) driven approach ... More
Emergence of Compositional Language with Deep Generational TransmissionApr 19 2019Consider a collaborative task that requires communication. Two agents are placed in an environment and must create a language from scratch in order to coordinate. Recent work has been interested in what kinds of languages emerge when deep reinforcement ... More
When is a Prediction Knowledge?Apr 18 2019Within Reinforcement Learning, there is a growing collection of research which aims to express all of an agent's knowledge of the world through predictions about sensation, behaviour, and time. This work can be seen not only as a collection of architectural ... More
Making Meaning: Semiotics Within Predictive Knowledge ArchitecturesApr 18 2019Within Reinforcement Learning, there is a fledgling approach to conceptualizing the environment in terms of predictions. Central to this predictive approach is the assertion that it is possible to construct ontologies in terms of predictions about sensation, ... More
Playgol: learning programs through playApr 18 2019Children learn though play. We introduce the analogous idea of learning programs through play. In this approach, a program induction system (the learner) is given a set of tasks and initial background knowledge. Before solving the tasks, the learner enters ... More
Exploring the Limitations of Behavior Cloning for Autonomous DrivingApr 18 2019Driving requires reacting to a wide variety of complex environment conditions and agent behaviors. Explicitly modeling each possible scenario is unrealistic. In contrast, imitation learning can, in theory, leverage data from large fleets of human-driven ... More
Intentional Computational Level DesignApr 18 2019The procedural generation of levels and content in video games is a challenging AI problem. Often such generation relies on an intelligent way of evaluating the content being generated so that constraints are satisfied and/or objectives maximized. In ... More
Codes, Functions, and Causes: A Critique of Brette's Conceptual Analysis of CodingApr 18 2019In a recent article, Brette argues that coding as a concept is inappropriate for explanations of neurocognitive phenomena. Here, we argue that Brette's conceptual analysis mischaracterizes the structure of causal claims in coding and other forms of analysis-by-decomposition. ... More
Interplanetary Transfers via Deep Representations of the Optimal Policy and/or of the Value FunctionApr 18 2019A number of applications to interplanetary trajectories have been recently proposed based on deep networks. These approaches often rely on the availability of a large number of optimal trajectories to learn from. In this paper we introduce a new method ... More
Influence Maximization via Representation LearningApr 18 2019Although influence maximization has been studied extensively in the past, the majority of works focus on the algorithmic aspect of the problem, overlooking several practical improvements that can be derived by data-driven observations or the inclusion ... More
4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural NetworksApr 18 2019In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms. ... More
ConvLab: Multi-Domain End-to-End Dialog System PlatformApr 18 2019We present ConvLab, an open-source multi-domain end-to-end dialog system platform, that enables researchers to quickly set up experiments with reusable components and compare a large set of different approaches, ranging from conventional pipeline systems ... More
Ontology-based Design of Experiments on Big Data SolutionsApr 18 2019Big data solutions are designed to cope with data of huge Volume and wide Variety, that need to be ingested at high Velocity and have potential Veracity issues, challenging characteristics that are usually referred to as the "4Vs of Big Data". In order ... More
Improving Interactive Reinforcement Agent Planning with Human DemonstrationApr 18 2019TAMER has proven to be a powerful interactive reinforcement learning method for allowing ordinary people to teach and personalize autonomous agents' behavior by providing evaluative feedback. However, a TAMER agent planning with UCT---a Monte Carlo Tree ... More
Explaining Deep Classification of Time-Series Data with Learned PrototypesApr 18 2019The emergence of deep learning networks raises a need for algorithms to explain their decisions so that users and domain experts can be confident using algorithmic recommendations for high-risk decisions. In this paper we leverage the information-rich ... More
Material Segmentation of Multi-View Satellite ImageryApr 17 2019Material recognition methods use image context and local cues for pixel-wise classification. In many cases only a single image is available to make a material prediction. Image sequences, routinely acquired in applications such as mutliview stereo, can ... More
Robust Exploration with Tight Bayesian Plausibility SetsApr 17 2019Optimism about the poorly understood states and actions is the main driving force of exploration for many provably-efficient reinforcement learning algorithms. We propose optimism in the face of sensible value functions (OFVF)- a novel data-driven Bayesian ... More
Off-Policy Policy Gradient with State Distribution CorrectionApr 17 2019We study the problem of off-policy policy optimization in Markov decision processes, and develop a novel off-policy policy gradient method. Prior off-policy policy gradient approaches have generally ignored the mismatch between the distribution of states ... More
Towards Evolutionary Theorem Proving for Isabelle/HOLApr 17 2019Mechanized theorem proving is becoming the basis of reliable systems programming and rigorous mathematics. Despite decades of progress in proof automation, writing mechanized proofs still requires engineers' expertise and remains labor intensive. Recently, ... More
Event-based Vision: A SurveyApr 17 2019Event cameras are bio-inspired sensors that work radically different from traditional cameras. Instead of capturing images at a fixed rate, they measure per-pixel brightness changes asynchronously. This results in a stream of events, which encode the ... More
Gaze Training by Modulated Dropout Improves Imitation LearningApr 17 2019Imitation learning by behavioral cloning is a prevalent method which has achieved some success in vision-based autonomous driving. The basic idea behind behavioral cloning is to have the neural network learn from observing a human expert's behavior. Typically, ... More
Guiding CTC Posterior Spike Timings for Improved Posterior Fusion and Knowledge DistillationApr 17 2019Conventional automatic speech recognition (ASR) systems trained from frame-level alignments can easily leverage posterior fusion to improve ASR accuracy and build a better single model with knowledge distillation. End-to-end ASR systems trained using ... More
Downhole Track Detection via Multiscale Conditional Generative Adversarial NetsApr 17 2019Frequent mine disasters cause a large number of casualties and property losses. Autonomous driving is a fundamental measure for solving this problem, and track detection is one of the key technologies for computer vision to achieve downhole automatic ... More
"Why did you do that?": Explaining black box models with Inductive SynthesisApr 17 2019By their nature, the composition of black box models is opaque. This makes the ability to generate explanations for the response to stimuli challenging. The importance of explaining black box models has become increasingly important given the prevalence ... More
Analysing Neural Network Topologies: a Game Theoretic ApproachApr 17 2019Artificial Neural Networks have shown impressive success in very different application cases. Choosing a proper network architecture is a critical decision for a network's success, usually done in a manual manner. As a straightforward strategy, large, ... More
3D Object Recognition with Ensemble Learning --- A Study of Point Cloud-Based Deep Learning ModelsApr 17 2019In this study, we present an analysis of model-based ensemble learning for 3D point-cloud object classification and detection. An ensemble of multiple model instances is known to outperform a single model instance, but there is little study of the topic ... More
An Exponential Lower Bound for the Runtime of the cGA on Jump FunctionsApr 17 2019In the first runtime analysis of an estimation-of-distribution algorithm (EDA) on the multi-modal jump function class, Hasen\"ohrl and Sutton (GECCO 2018) proved that the runtime of the compact genetic algorithm with suitable parameter choice on jump ... More
Bayesian policy selection using active inferenceApr 17 2019Learning to take actions based on observations is a core requirement for artificial agents to be able to be successful and robust at their task. Reinforcement Learn-ing (RL) is a well-known technique for learning such policies. However, current RL algorithms ... More
MHP-VOS: Multiple Hypotheses Propagation for Video Object SegmentationApr 17 2019We address the problem of semi-supervised video object segmentation (VOS), where the masks of objects of interests are given in the first frame of an input video. To deal with challenging cases where objects are occluded or missing, previous work relies ... More
Explainability in Human-Agent SystemsApr 17 2019This paper presents a taxonomy of explainability in Human-Agent Systems. We consider fundamental questions about the Why, Who, What, When and How of explainability. First, we define explainability, and its relationship to the related terms of interpretability, ... More
A Survey on Traffic Signal Control MethodsApr 17 2019Traffic signal control is an important and challenging real-world problem, which aims to minimize the travel time of vehicles by coordinating their movements at the road intersections. Current traffic signal control systems in use still rely heavily on ... More
Contextual Aware Joint Probability Model Towards Question Answering SystemApr 17 2019In this paper, we address the question answering challenge with the SQuAD 2.0 dataset. We design a model architecture which leverages BERT's capability of context-aware word embeddings and BiDAF's context interactive exploration mechanism. By integrating ... More
DENet: A Universal Network for Counting Crowd with Varying Densities and ScalesApr 17 2019Counting people or objects with significantly varying scales and densities has attracted much interest from the research community and yet it remains an open problem. In this paper, we propose a simple but an efficient and effective network, named DENet, ... More
How to define co-occurrence in different domains of study?Apr 16 2019This position paper presents a comparative study of co-occurrences. Some similarities and differences in the definition exist depending on the research domain (e.g. linguistics, NLP, computer science). This paper discusses these points, and deals with ... More
Devil is in the Edges: Learning Semantic Boundaries from Noisy AnnotationsApr 16 2019We tackle the problem of semantic boundary prediction, which aims to identify pixels that belong to object(class) boundaries. We notice that relevant datasets consist of a significant level of label noise, reflecting the fact that precise annotations ... More
Matrix and tensor decompositions for training binary neural networksApr 16 2019This paper is on improving the training of binary neural networks in which both activations and weights are binary. While prior methods for neural network binarization binarize each filter independently, we propose to instead parametrize the weight tensor ... More
Usage of Decision Support Systems for Conflicts Modelling during Information Operations RecognitionApr 16 2019Application of decision support systems for conflict modeling in information operations recognition is presented. An information operation is considered as a complex weakly structured system. The model of conflict between two subjects is proposed based ... More
Simion Zoo: A Workbench for Distributed Experimentation with Reinforcement Learning for Continuous Control TasksApr 16 2019We present Simion Zoo, a Reinforcement Learning (RL) workbench that provides a complete set of tools to design, run, and analyze the results,both statistically and visually, of RL control applications. The main features that set apart Simion Zoo from ... More
Learning 3D Navigation Protocols on Touch Interfaces with Cooperative Multi-Agent Reinforcement LearningApr 16 2019Using touch devices to navigate in virtual 3D environments such as computer assisted design (CAD) models or geographical information systems (GIS) is inherently difficult for humans, as the 3D operations have to be performed by the user on a 2D touch ... More
A Pattern-Hierarchy Classifier for Reduced TeachingApr 16 2019This paper uses a branching classifier mechanism in an unsupervised scenario, to enable it to self-organise data into unknown categories. A teaching phase is then able to help the classifier to learn the true category for each input row, using a reduced ... More
Relation-Shape Convolutional Neural Network for Point Cloud AnalysisApr 16 2019Point cloud analysis is very challenging, as the shape implied in irregular points is difficult to capture. In this paper, we propose RS-CNN, namely, Relation-Shape Convolutional Neural Network, which extends regular grid CNN to irregular configuration ... More
Theoretical Foundations of Defeasible Description LogicsApr 16 2019We extend description logics (DLs) with non-monotonic reasoning features. We start by investigating a notion of defeasible subsumption in the spirit of defeasible conditionals as studied by Kraus, Lehmann and Magidor in the propositional case. In particular, ... More
Disentangling Pose from Appearance in Monochrome Hand ImagesApr 16 2019Hand pose estimation from the monocular 2D image is challenging due to the variation in lighting, appearance, and background. While some success has been achieved using deep neural networks, they typically require collecting a large dataset that adequately ... More
Method for Constructing Artificial Intelligence Player with Abstraction to Markov Decision Processes in Multiplayer Game of MahjongApr 16 2019We propose a method for constructing artificial intelligence (AI) of mahjong, which is a multiplayer imperfect information game. Since the size of the game tree is huge, constructing an expert-level AI player of mahjong is challenging. We define multiple ... More
Object-Oriented Dynamics Learning through Multi-Level AbstractionApr 16 2019Object-based approaches for learning action-conditioned dynamics has demonstrated promise for generalization and interpretability. However, existing approaches suffer from structural limitations and optimization difficulties for common environments with ... More
An extended description logic system with knowledge element based on ALCApr 16 2019With the rise of knowledge management and knowledge economy, the knowledge elements that directly link and embody the knowledge system have become the research focus and hotspot in certain areas. The existing knowledge element representation methods are ... More
Deep Neural Network Based Hyperspectral Pixel Classification With Factorized Spectral-Spatial Feature RepresentationApr 16 2019Deep learning has been widely used for hyperspectral pixel classification due to its ability of generating deep feature representation. However, how to construct an efficient and powerful network suitable for hyperspectral data is still under exploration. ... More
Counterfactual Visual ExplanationsApr 16 2019A counterfactual query is typically of the form 'For situation X, why was the outcome Y and not Z?'. A counterfactual explanation (or response to such a query) is of the form "If X was X*, then the outcome would have been Z rather than Y." In this work, ... More
A Solution for Dynamic Spectrum Management in Mission-Critical UAV NetworksApr 16 2019In this paper, we study the problem of spectrum scarcity in a network of unmanned aerial vehicles (UAVs) during mission-critical applications such as disaster monitoring and public safety missions, where the pre-allocated spectrum is not sufficient to ... More
Helping IT and OT Defenders CollaborateApr 16 2019Cyber-physical systems, especially in critical infrastructures, have become primary hacking targets in international conflicts and diplomacy. However, cyber-physical systems present unique challenges to defenders, starting with an inability to communicate. ... More
Efficiently Exploring Ordering Problems through Conflict-directed SearchApr 15 2019In planning and scheduling, solving problems with both state and temporal constraints is hard since these constraints may be highly coupled. Judicious orderings of events enable solvers to efficiently make decisions over sequences of actions to satisfy ... More
Efficient Supervision for Robot Learning via Imitation, Simulation, and AdaptationApr 15 2019Recent successes in machine learning have led to a shift in the design of autonomous systems, improving performance on existing tasks and rendering new applications possible. Data-focused approaches gain relevance across diverse, intricate applications ... More
Introduction to Multi-Armed BanditsApr 15 2019Multi-armed bandits a simple but very powerful framework for algorithms that make decisions over time under uncertainty. An enormous body of work has accumulated over the years, covered in several books and surveys. This book provides a more introductory, ... More
Low-Power Computer Vision: Status, Challenges, OpportunitiesApr 15 2019Computer vision has achieved impressive progress in recent years. Meanwhile, mobile phones have become the primary computing platforms for millions of people. In addition to mobile phones, many autonomous systems rely on visual data for making decisions ... More
Tutorial: Safe and Reliable Machine LearningApr 15 2019This document serves as a brief overview of the "Safe and Reliable Machine Learning" tutorial given at the 2019 ACM Conference on Fairness, Accountability, and Transparency (FAT* 2019). The talk slides can be found here: https://bit.ly/2Gfsukp, while ... More
Reinforcement Learning with Probabilistic Guarantees for Autonomous DrivingApr 15 2019Designing reliable decision strategies for autonomous urban driving is challenging. Reinforcement learning (RL) has been used to automatically derive suitable behavior in uncertain environments, but it does not provide any guarantee on the performance ... More
Synthetic Neural Vision System Design for Motion Pattern Recognition in Dynamic Robot ScenesApr 15 2019Insects have tiny brains but complicated visual systems for motion perception. A handful of insect visual neurons have been computationally modeled and successfully applied for robotics. How different neurons collaborate on motion perception, is an open ... More
Multi-Objective Autonomous Braking System using Naturalistic DatasetApr 15 2019A deep reinforcement learning based multi-objective autonomous braking system is presented. The design of the system is formulated in a continuous action space and seeks to maximize both pedestrian safety and perception as well as passenger comfort. The ... More
Processsing Simple Geometric Attributes with AutoencodersApr 15 2019Image synthesis is a core problem in modern deep learning, and many recent architectures such as autoencoders and Generative Adversarial networks produce spectacular results on highly complex data, such as images of faces or landscapes. While these results ... More
A deep learning framework for quality assessment and restoration in video endoscopyApr 15 2019Endoscopy is a routine imaging technique used for both diagnosis and minimally invasive surgical treatment. Artifacts such as motion blur, bubbles, specular reflections, floating objects and pixel saturation impede the visual interpretation and the automated ... More
Three scenarios for continual learningApr 15 2019Standard artificial neural networks suffer from the well-known issue of catastrophic forgetting, making continual or lifelong learning difficult for machine learning. In recent years, numerous methods have been proposed for continual learning, but due ... More
Human-Guided Learning of Column Networks: Augmenting Deep Learning with AdviceApr 15 2019Recently, deep models have been successfully applied in several applications, especially with low-level representations. However, sparse, noisy samples and structured domains (with multiple objects and interactions) are some of the open challenges in ... More
Learning Deformable Kernels for Image and Video DenoisingApr 15 2019Most of the classical denoising methods restore clear results by selecting and averaging pixels in the noisy input. Instead of relying on hand-crafted selecting and averaging strategies, we propose to explicitly learn this process with deep neural networks. ... More
Improving interactive reinforcement learning: What makes a good teacher?Apr 15 2019Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which uses a parent-like ... More
Predicting human decisions with behavioral theories and machine learningApr 15 2019Behavioral decision theories aim to explain human behavior. Can they help predict it? An open tournament for prediction of human choices in fundamental economic decision tasks is presented. The results suggest that integration of certain behavioral theories ... More
Deep CNNs Meet Global Covariance Pooling: Better Representation and GeneralizationApr 15 2019Compared with global average pooling in existing deep convolutional neural networks (CNNs), global covariance pooling can capture richer statistics of deep features, having potential for improving representation and generalization abilities of deep CNNs. ... More
Personalized Context-aware Re-ranking for E-commerce Recommender SystemsApr 15 2019Ranking is a core task in E-commerce recommender systems, which aims at providing an ordered list of items to users. Typically, a ranking function is learned from the labeled dataset to optimize the global performance, which produces a ranking score for ... More
Differential Privacy for Eye-Tracking DataApr 15 2019As large eye-tracking datasets are created, data privacy is a pressing concern for the eye-tracking community. De-identifying data does not guarantee privacy because multiple datasets can be linked for inferences. A common belief is that aggregating individuals' ... More
Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image TranslationApr 15 2019Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible ... More
Multi-Channel Attention Selection GAN with Cascaded Semantic Guidance for Cross-View Image TranslationApr 15 2019Apr 16 2019Cross-view image translation is challenging because it involves images with drastically different views and severe deformation. In this paper, we propose a novel approach named Multi-Channel Attention SelectionGAN (SelectionGAN) that makes it possible ... More
Curious iLQR: Resolving Uncertainty in Model-based RLApr 15 2019Curiosity as a means to explore during reinforcement learning problems has recently become very popular. However, very little progress has been made in utilizing curiosity for learning control. In this work, we propose a model-based reinforcement learning ... More
A Short Survey On Memory Based Reinforcement LearningApr 14 2019Reinforcement learning (RL) is a branch of machine learning which is employed to solve various sequential decision making problems without proper supervision. Due to the recent advancement of deep learning, the newly proposed Deep-RL algorithms have been ... More
Text segmentation on multilabel documents: A distant-supervised approachApr 14 2019Segmenting text into semantically coherent segments is an important task with applications in information retrieval and text summarization. Developing accurate topical segmentation requires the availability of training data with ground truth information ... More
Distributed representation of multi-sense words: A loss-driven approachApr 14 2019Word2Vec's Skip Gram model is the current state-of-the-art approach for estimating the distributed representation of words. However, it assumes a single vector per word, which is not well-suited for representing words that have multiple senses. This work ... More
Dot-to-Dot: Achieving Structured Robotic Manipulation through Hierarchical Reinforcement LearningApr 14 2019Robotic systems are ever more capable of automation and fulfilment of complex tasks, particularly with reliance on recent advances in intelligent systems, deep learning and artificial intelligence in general. However, as robots and humans come closer ... More
LiveSketch: Query Perturbations for Guided Sketch-based Visual SearchApr 14 2019LiveSketch is a novel algorithm for searching large image collections using hand-sketched queries. LiveSketch tackles the inherent ambiguity of sketch search by creating visual suggestions that augment the query as it is drawn, making query specification ... More
HAKE: Human Activity Knowledge EngineApr 13 2019Human activity understanding is crucial for building automatic intelligent system. With the help of deep learning, activity understanding has made huge progress recently. But some challenges such as imbalanced data distribution, action ambiguity, complex ... More
Improving Distantly-supervised Entity Typing with Compact Latent Space ClusteringApr 13 2019Recently, distant supervision has gained great success on Fine-grained Entity Typing (FET). Despite its efficiency in reducing manual labeling efforts, it also brings the challenge of dealing with false entity type labels, as distant supervision assigns ... More
Temporal Network Representation LearningApr 12 2019Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately ... More
Incremental multi-domain learning with network latent tensor factorizationApr 12 2019The prominence of deep learning, large amount of annotated data and increasingly powerful hardware made it possible to reach remarkable performance for supervised classification tasks, in many cases saturating the training sets. However, adapting the ... More
Few-Shot Bayesian Imitation Learning with Logic over ProgramsApr 12 2019We describe an expressive class of policies that can be efficiently learned from a few demonstrations. Policies are represented as logical combinations of programs drawn from a small domain-specific language (DSL). We define a prior over policies with ... More
Let's Play Again: Variability of Deep Reinforcement Learning Agents in Atari EnvironmentsApr 12 2019Reproducibility in reinforcement learning is challenging: uncontrolled stochasticity from many sources, such as the learning algorithm, the learned policy, and the environment itself have led researchers to report the performance of learned agents using ... More
A Reference Vector based Many-Objective Evolutionary Algorithm with Feasibility-aware AdaptationApr 12 2019The infeasible parts of the objective space in difficult many-objective optimization problems cause trouble for evolutionary algorithms. This paper proposes a reference vector based algorithm which uses two interacting engines to adapt the reference vectors ... More
Similarities between policy gradient methods (PGM) in Reinforcement learning (RL) and supervised learning (SL)Apr 12 2019Reinforcement learning (RL) is about sequential decision making and is traditionally opposed to supervised learning (SL) and unsupervised learning (USL). In RL, given the current state, the agent makes a decision that may influence the next state as opposed ... More
Generative Hybrid Representations for Activity Forecasting with No-Regret LearningApr 12 2019Automatically reasoning about future human behaviors is a difficult problem with significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors. Some behaviors, ... More
Interpretable Classification from Skin Cancer Histology Slides Using Deep Learning: A Retrospective Multicenter StudyApr 12 2019For diagnosing melanoma, hematoxylin and eosin (H&E) stained tissue slides remains the gold standard. These images contain quantitative information in different magnifications. In the present study, we investigated whether deep convolutional neural networks ... More
Deep Policies for Width-Based Planning in Pixel DomainsApr 12 2019Width-based planning has demonstrated great success in recent years due to its ability to scale independently of the size of the state space. For example, Bandres et al. (2018) introduced a rollout version of the Iterated Width algorithm whose performance ... More
Evolved Art with Transparent, Overlapping, and Geometric ShapesApr 12 2019In this work, an evolutionary art project is presented where images are approximated by transparent, overlapping and geometric shapes of different types, e.g., polygons, circles, lines. Genotypes representing features and order of the geometric shapes ... More
Interaction-aware Decision Making with Adaptive Strategies under Merging ScenariosApr 12 2019In order to drive safely and efficiently under merging scenarios, autonomous vehicles should be aware of their surroundings and make decisions by interacting with other road participants. Moreover, different strategies should be made when the autonomous ... More
TAFE-Net: Task-Aware Feature Embeddings for Low Shot LearningApr 11 2019Learning good feature embeddings for images often requires substantial training data. As a consequence, in settings where training data is limited (e.g., few-shot and zero-shot learning), we are typically forced to use a generic feature embedding across ... More
MRI Tissue Magnetism Quantification through Total Field Inversion with Deep Neural NetworksApr 11 2019Quantitative susceptibility mapping (QSM) utilizes MRI signal phase to infer estimates of local tissue magnetism (magnetic susceptibility), which has been shown useful to provide novel image contrast and as biomarkers of abnormal tissue. QSM requires ... More
Experimental neural network enhanced quantum tomographyApr 11 2019Quantum tomography is currently ubiquitous for testing any implementation of a quantum information processing device. Various sophisticated procedures for state and process reconstruction from measured data are well developed and benefit from precise ... More
Factor Graph AttentionApr 11 2019Dialog is an effective way to exchange information, but subtle details and nuances are extremely important. While significant progress has paved a path to address visual dialog with algorithms, details and nuances remain a challenge. Attention mechanisms ... More
Two Body Problem: Collaborative Visual Task CompletionApr 11 2019Collaboration is a necessary skill to perform tasks that are beyond one agent's capabilities. Addressed extensively in both conventional and modern AI, multi-agent collaboration has often been studied in the context of simple grid worlds. We argue that ... More
A Simple Baseline for Audio-Visual Scene-Aware DialogApr 11 2019The recently proposed audio-visual scene-aware dialog task paves the way to a more data-driven way of learning virtual assistants, smart speakers and car navigation systems. However, very little is known to date about how to effectively extract meaningful ... More