January 28, 2020

3053 words 15 mins read

Paper Group ANR 847

Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network. Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs. A hybrid text normalization system using multi-head self-attention for mandarin. Cross-Domain Image Manipulation by Demonstration. A Theoreti …

Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network


Title	Fully-automatic segmentation of kidneys in clinical ultrasound images using a boundary distance regression network
Authors	Shi Yin, Zhengqiang Zhang, Hongming Li, Qinmu Peng, Xinge You, Susan L. Furth, Gregory E. Tasian, Yong Fan
Abstract	It remains challenging to automatically segment kidneys in clinical ultrasound images due to the kidneys’ varied shapes and image intensity distributions, although semi-automatic methods have achieved promising performance. In this study, we developed a novel boundary distance regression deep neural network to segment the kidneys, informed by the fact that the kidney boundaries are relatively consistent across images in terms of their appearance. Particularly, we first use deep neural networks pre-trained for classification of natural images to extract high-level image features from ultrasound images, then these feature maps are used as input to learn kidney boundary distance maps using a boundary distance regression network, and finally the predicted boundary distance maps are classified as kidney pixels or non-kidney pixels using a pixel classification network in an end-to-end learning fashion. Experimental results have demonstrated that our method could effectively improve the performance of automatic kidney segmentation, significantly better than deep learning based pixel classification networks.
Tasks
Published	2019-01-05
URL	http://arxiv.org/abs/1901.01982v1
PDF	http://arxiv.org/pdf/1901.01982v1.pdf
PWC	https://paperswithcode.com/paper/fully-automatic-segmentation-of-kidneys-in
Repo
Framework

Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs


Title	Problem Dependent Reinforcement Learning Bounds Which Can Identify Bandit Structure in MDPs
Authors	Andrea Zanette, Emma Brunskill
Abstract	In order to make good decision under uncertainty an agent must learn from observations. To do so, two of the most common frameworks are Contextual Bandits and Markov Decision Processes (MDPs). In this paper, we study whether there exist algorithms for the more general framework (MDP) which automatically provide the best performance bounds for the specific problem at hand without user intervention and without modifying the algorithm. In particular, it is found that a very minor variant of a recently proposed reinforcement learning algorithm for MDPs already matches the best possible regret bound $\tilde O (\sqrt{SAT})$ in the dominant term if deployed on a tabular Contextual Bandit problem despite the agent being agnostic to such setting.
Tasks	Multi-Armed Bandits
Published	2019-11-03
URL	https://arxiv.org/abs/1911.00954v1
PDF	https://arxiv.org/pdf/1911.00954v1.pdf
PWC	https://paperswithcode.com/paper/problem-dependent-reinforcement-learning-1
Repo
Framework

A hybrid text normalization system using multi-head self-attention for mandarin


Title	A hybrid text normalization system using multi-head self-attention for mandarin
Authors	Junhui Zhang, Junjie Pan, Xiang Yin, Chen Li, Shichao Liu, Yang Zhang, Yuxuan Wang, Zejun Ma
Abstract	In this paper, we propose a hybrid text normalization system using multi-head self-attention. The system combines the advantages of a rule-based model and a neural model for text preprocessing tasks. Previous studies in Mandarin text normalization usually use a set of hand-written rules, which are hard to improve on general cases. The idea of our proposed system is motivated by the neural models from recent studies and has a better performance on our internal news corpus. This paper also includes different attempts to deal with imbalanced pattern distribution of the dataset. Overall, the performance of the system is improved by over 1.5% on sentence-level and it has a potential to improve further.
Tasks
Published	2019-11-11
URL	https://arxiv.org/abs/1911.04128v2
PDF	https://arxiv.org/pdf/1911.04128v2.pdf
PWC	https://paperswithcode.com/paper/a-hybrid-text-normalization-system-using
Repo
Framework

Cross-Domain Image Manipulation by Demonstration


Title	Cross-Domain Image Manipulation by Demonstration
Authors	Ben Usman, Nick Dufour, Kate Saenko, Chris Bregler
Abstract	In this work we propose a model that can manipulate individual visual attributes of objects in a real scene using examples of how respective attribute manipulations affect the output of a simulation. As an example, we train our model to manipulate the expression of a human face using nonphotorealistic 3D renders of a face with varied expression. Our model manages to preserve all other visual attributes of a real face, such as head orientation, even though this and other attributes are not labeled in either real or synthetic domain. Since our model learns to manipulate a specific property in isolation using only “synthetic demonstrations” of such manipulations without explicitly provided labels, it can be applied to shape, texture, lighting, and other properties that are difficult to measure or represent as real-valued vectors. We measure the degree to which our model preserves other attributes of a real image when a single specific attribute is manipulated. We use digit datasets to analyze how discrepancy in attribute distributions affects the performance of our model, and demonstrate results in a far more difficult setting: learning to manipulate real human faces using nonphotorealistic 3D renders.
Tasks
Published	2019-01-28
URL	http://arxiv.org/abs/1901.10024v2
PDF	http://arxiv.org/pdf/1901.10024v2.pdf
PWC	https://paperswithcode.com/paper/puppetgan-transferring-disentangled
Repo
Framework

A Theoretical Analysis of Contrastive Unsupervised Representation Learning


Title	A Theoretical Analysis of Contrastive Unsupervised Representation Learning
Authors	Sanjeev Arora, Hrishikesh Khandeparkar, Mikhail Khodak, Orestis Plevrakis, Nikunj Saunshi
Abstract	Recent empirical works have successfully used unlabeled data to learn feature representations that are broadly useful in downstream classification tasks. Several of these methods are reminiscent of the well-known word2vec embedding algorithm: leveraging availability of pairs of semantically “similar” data points and “negative samples,” the learner forces the inner product of representations of similar pairs with each other to be higher on average than with negative samples. The current paper uses the term contrastive learning for such algorithms and presents a theoretical framework for analyzing them by introducing latent classes and hypothesizing that semantically similar points are sampled from the same latent class. This framework allows us to show provable guarantees on the performance of the learned representations on the average classification task that is comprised of a subset of the same set of latent classes. Our generalization bound also shows that learned representations can reduce (labeled) sample complexity on downstream tasks. We conduct controlled experiments in both the text and image domains to support the theory.
Tasks	Representation Learning, Unsupervised Representation Learning
Published	2019-02-25
URL	http://arxiv.org/abs/1902.09229v1
PDF	http://arxiv.org/pdf/1902.09229v1.pdf
PWC	https://paperswithcode.com/paper/a-theoretical-analysis-of-contrastive
Repo
Framework

Dissecting Content and Context in Argumentative Relation Analysis


Title	Dissecting Content and Context in Argumentative Relation Analysis
Authors	Juri Opitz, Anette Frank
Abstract	When assessing relations between argumentative units (e.g., support or attack), computational systems often exploit disclosing indicators or markers that are not part of elementary argumentative units (EAUs) themselves, but are gained from their context (position in paragraph, preceding tokens, etc.). We show that this dependency is much stronger than previously assumed. In fact, we show that by completely masking the EAU text spans and only feeding information from their context, a competitive system may function even better. We argue that an argument analysis system that relies more on discourse context than the argument’s content is unsafe, since it can easily be tricked. To alleviate this issue, we separate argumentative units from their context such that the system is forced to model and rely on an EAU’s content. We show that the resulting classification system is more robust, and argue that such models are better suited for predicting argumentative relations across documents.
Tasks
Published	2019-06-07
URL	https://arxiv.org/abs/1906.03338v1
PDF	https://arxiv.org/pdf/1906.03338v1.pdf
PWC	https://paperswithcode.com/paper/dissecting-content-and-context-in
Repo
Framework

Enhancement of Power Equipment Management Using Knowledge Graph


Title	Enhancement of Power Equipment Management Using Knowledge Graph
Authors	Yachen Tang, Tingting Liu, Guangyi Liu, Jie Li, Renchang Dai, Chen Yuan
Abstract	Accurate retrieval of the power equipment information plays an important role in guiding the full-lifecycle management of power system assets. Because of data duplication, database decentralization, weak data relations, and sluggish data updates, the power asset management system eager to adopt a new strategy to avoid the information losses, bias, and improve the data storage efficiency and extraction process. Knowledge graph has been widely developed in large part owing to its schema-less nature. It enables the knowledge graph to grow seamlessly and allows new relations addition and entities insertion when needed. This study proposes an approach for constructing power equipment knowledge graph by merging existing multi-source heterogeneous power equipment related data. A graph-search method to illustrate exhaustive results to the desired information based on the constructed knowledge graph is proposed. A case of a 500 kV station example is then demonstrated to show relevant search results and to explain that the knowledge graph can improve the efficiency of power equipment management.
Tasks
Published	2019-04-28
URL	http://arxiv.org/abs/1904.12242v1
PDF	http://arxiv.org/pdf/1904.12242v1.pdf
PWC	https://paperswithcode.com/paper/enhancement-of-power-equipment-management
Repo
Framework

Stochastic Gradient Annealed Importance Sampling for Efficient Online Marginal Likelihood Estimation


Title	Stochastic Gradient Annealed Importance Sampling for Efficient Online Marginal Likelihood Estimation
Authors	Scott A. Cameron, Hans C. Eggers, Steve Kroon
Abstract	We consider estimating the marginal likelihood in settings with independent and identically distributed (i.i.d.) data. We propose estimating the predictive distributions in a sequential factorization of the marginal likelihood in such settings by using stochastic gradient Markov Chain Monte Carlo techniques. This approach is far more efficient than traditional marginal likelihood estimation techniques such as nested sampling and annealed importance sampling due to its use of mini-batches to approximate the likelihood. Stability of the estimates is provided by an adaptive annealing schedule. The resulting stochastic gradient annealed importance sampling (SGAIS) technique, which is the key contribution of our paper, enables us to estimate the marginal likelihood of a number of models considerably faster than traditional approaches, with no noticeable loss of accuracy. An important benefit of our approach is that the marginal likelihood is calculated in an online fashion as data becomes available, allowing the estimates to be used for applications such as online weighted model combination.
Tasks
Published	2019-11-17
URL	https://arxiv.org/abs/1911.07337v1
PDF	https://arxiv.org/pdf/1911.07337v1.pdf
PWC	https://paperswithcode.com/paper/stochastic-gradient-annealed-importance
Repo
Framework

Local Fourier Slice Photography


Title	Local Fourier Slice Photography
Authors	Christian Lessig
Abstract	Light field cameras provide intriguing possibilities, such as post-capture refocus or the ability to synthesize images from novel viewpoints. This comes, however, at the price of significant storage requirements. Compression techniques can be used to reduce these but refocusing and reconstruction require so far again a dense pixel representation. To avoid this, we introduce local Fourier slice photography that allows for refocused image reconstruction directly from a sparse wavelet representation of a light field, either to obtain an image or a compressed representation of it. The result is made possible by wavelets that respect the “slicing’s” intrinsic structure and enable us to derive exact reconstruction filters for the refocused image in closed form. Image reconstruction then amounts to applying these filters to the light field’s wavelet coefficients, and hence no reconstruction of a dense pixel representation is required. We demonstrate that this substantially reduces storage requirements and also computation times. We furthermore analyze the computational complexity of our algorithm and show that it scales linearly with the size of the reconstructed region and the non-negligible wavelet coefficients, i.e. with the visual complexity.
Tasks	Image Reconstruction
Published	2019-02-16
URL	https://arxiv.org/abs/1902.06082v2
PDF	https://arxiv.org/pdf/1902.06082v2.pdf
PWC	https://paperswithcode.com/paper/local-fourier-slice-photography
Repo
Framework

2-D Cluster Variation Method Free Energy: Fundamentals and Pragmatics


Title	2-D Cluster Variation Method Free Energy: Fundamentals and Pragmatics
Authors	Alianna J. Maren
Abstract	Despite being invented in 1951 by R. Kikuchi, the 2-D Cluster Variation Method (CVM), has not yet received attention. Nevertheless, this method can usefully characterize 2-D topographies using just two parameters; the activation enthalpy and the interaction enthalpy. This Technical Report presents 2-D CVM details, including the dependence of the various configuration variables on the enthalpy parameters, as well as illustrations of various topographies (ranging from scale-free-like to rich club-like) that result from different parameter selection. The complete derivation for the analytic solution, originally presented simply as a result in Kikuchi and Brush (1967) is given here, along with careful comparison of the analytically-predicted configuration variables versus those obtained when performing computational free energy minimization on a 2-D grid. The 2-D CVM can potentially function as a secondary free energy minimization within the hidden layer of a neural network, providing a basis for extending node activations over time and allowing temporal correlation of patterns.
Tasks
Published	2019-09-20
URL	https://arxiv.org/abs/1909.09366v1
PDF	https://arxiv.org/pdf/1909.09366v1.pdf
PWC	https://paperswithcode.com/paper/2-d-cluster-variation-method-free-energy
Repo
Framework

Knowledge Distillation for End-to-End Person Search


Title	Knowledge Distillation for End-to-End Person Search
Authors	Bharti Munjal, Fabio Galasso, Sikandar Amin
Abstract	We introduce knowledge distillation for end-to-end person search. End-to-End methods are the current state-of-the-art for person search that solve both detection and re-identification jointly. These approaches for joint optimization show their largest drop in performance due to a sub-optimal detector. We propose two distinct approaches for extra supervision of end-to-end person search methods in a teacher-student setting. The first is adopted from state-of-the-art knowledge distillation in object detection. We employ this to supervise the detector of our person search model at various levels using a specialized detector. The second approach is new, simple and yet considerably more effective. This distills knowledge from a teacher re-identification technique via a pre-computed look-up table of ID features. It relaxes the learning of identification features and allows the student to focus on the detection task. This procedure not only helps fixing the sub-optimal detector training in the joint optimization and simultaneously improving the person search, but also closes the performance gap between the teacher and the student for model compression in this case. Overall, we demonstrate significant improvements for two recent state-of-the-art methods using our proposed knowledge distillation approach on two benchmark datasets. Moreover, on the model compression task our approach brings the performance of smaller models on par with the larger models.
Tasks	Model Compression, Object Detection, Person Search
Published	2019-09-03
URL	https://arxiv.org/abs/1909.01058v2
PDF	https://arxiv.org/pdf/1909.01058v2.pdf
PWC	https://paperswithcode.com/paper/knowledge-distillation-for-end-to-endperson
Repo
Framework

Off-Policy Actor-Critic with Shared Experience Replay


Title	Off-Policy Actor-Critic with Shared Experience Replay
Authors	Simon Schmitt, Matteo Hessel, Karen Simonyan
Abstract	We investigate the combination of actor-critic reinforcement learning algorithms with uniform large-scale experience replay and propose solutions for two challenges: (a) efficient actor-critic learning with experience replay (b) stability of off-policy learning where agents learn from other agents behaviour. We employ those insights to accelerate hyper-parameter sweeps in which all participating agents run concurrently and share their experience via a common replay module. To this end we analyze the bias-variance tradeoffs in V-trace, a form of importance sampling for actor-critic methods. Based on our analysis, we then argue for mixing experience sampled from replay with on-policy experience, and propose a new trust region scheme that scales effectively to data distributions where V-trace becomes unstable. We provide extensive empirical validation of the proposed solution. We further show the benefits of this setup by demonstrating state-of-the-art data efficiency on Atari among agents trained up until 200M environment frames.
Tasks	Atari Games
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11583v2
PDF	https://arxiv.org/pdf/1909.11583v2.pdf
PWC	https://paperswithcode.com/paper/off-policy-actor-critic-with-shared-1
Repo
Framework

Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning


Title	Directed-Weighting Group Lasso for Eltwise Blocked CNN Pruning
Authors	Ke Zhan, Shimiao Jiang, Yu Bai, Yi Li, Xu Liu, Zhuoran Xu
Abstract	Eltwise layer is a commonly used structure in the multi-branch deep learning network. In a filter-wise pruning procedure, due to the specific operation of the eltwise layer, all its previous convolutional layers should vote for which filters by index should be pruned. Since only an intersection of the voted filters is pruned, the compression rate is limited. This work proposes a method called Directed-Weighting Group Lasso (DWGL), which enforces an index-wise incremental (directed) coefficient on the filterlevel group lasso items, so that the low index filters getting high activation tend to be kept while the high index ones tend to be pruned. When using DWGL, much fewer filters are retained during the voting process and the compression rate can be boosted. The paper test the proposed method on the ResNet series networks. On CIFAR-10, it achieved a 75.34% compression rate on ResNet-56 with a 0.94% error increment, and a 52.06% compression rate on ResNet-20 with a 0.72% error increment. On ImageNet, it achieved a 53% compression rate with ResNet-50 with a 0.6% error increment, speeding up the network by 2.23 times. Furthermore, it achieved a 75% compression rate on ResNet-50 with a 1.2% error increment, speeding up the network by 4 times.
Tasks
Published	2019-10-21
URL	https://arxiv.org/abs/1910.09318v1
PDF	https://arxiv.org/pdf/1910.09318v1.pdf
PWC	https://paperswithcode.com/paper/directed-weighting-group-lasso-for-eltwise
Repo
Framework

DisCoRL: Continual Reinforcement Learning via Policy Distillation


Title	DisCoRL: Continual Reinforcement Learning via Policy Distillation
Authors	René Traoré, Hugo Caselles-Dupré, Timothée Lesort, Te Sun, Guanghang Cai, Natalia Díaz-Rodríguez, David Filliat
Abstract	In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of those policies applying without an external signal. In the case of continual reinforcement learning a third challenge arises: learning tasks sequentially without forgetting the previous ones. In this paper, we tackle these challenges by proposing DisCoRL, an approach combining state representation learning and policy distillation. We experiment on a sequence of three simulated 2D navigation tasks with a 3 wheel omni-directional robot. Moreover, we tested our approach’s robustness by transferring the final policy into a real life setting. The policy can solve all tasks and automatically infer which one to run.
Tasks	Representation Learning
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05855v1
PDF	https://arxiv.org/pdf/1907.05855v1.pdf
PWC	https://paperswithcode.com/paper/discorl-continual-reinforcement-learning-via
Repo
Framework

Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis


Title	Improving Few-Shot User-Specific Gaze Adaptation via Gaze Redirection Synthesis
Authors	Yu Yu, Gang Liu, Jean-Marc Odobez
Abstract	As an indicator of human attention gaze is a subtle behavioral cue which can be exploited in many applications. However, inferring 3D gaze direction is challenging even for deep neural networks given the lack of large amount of data (groundtruthing gaze is expensive and existing datasets use different setups) and the inherent presence of gaze biases due to person-specific difference. In this work, we address the problem of person-specific gaze model adaptation from only a few reference training samples. The main and novel idea is to improve gaze adaptation by generating additional training samples through the synthesis of gaze-redirected eye images from existing reference samples. In doing so, our contributions are threefold: (i) we design our gaze redirection framework from synthetic data, allowing us to benefit from aligned training sample pairs to predict accurate inverse mapping fields; (ii) we proposed a self-supervised approach for domain adaptation; (iii) we exploit the gaze redirection to improve the performance of person-specific gaze estimation. Extensive experiments on two public datasets demonstrate the validity of our gaze retargeting and gaze estimation framework.
Tasks	Domain Adaptation, Gaze Estimation
Published	2019-04-24
URL	http://arxiv.org/abs/1904.10638v1
PDF	http://arxiv.org/pdf/1904.10638v1.pdf
PWC	https://paperswithcode.com/paper/improving-few-shot-user-specific-gaze
Repo
Framework