January 30, 2020

2536 words 12 mins read

Paper Group ANR 261

Reconstructing Network Inputs with Additive Perturbation Signatures. 3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion. Semi-supervised Learning of Fetal Anatomy from Ultrasound. Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry. Variable Neighborhood Search for the …

Reconstructing Network Inputs with Additive Perturbation Signatures


Title	Reconstructing Network Inputs with Additive Perturbation Signatures
Authors	Nick Moran, Chiraag Juvekar
Abstract	In this work, we present preliminary results demonstrating the ability to recover a significant amount of information about secret model inputs given only very limited access to model outputs and the ability evaluate the model on additive perturbations to the input.
Tasks
Published	2019-04-11
URL	http://arxiv.org/abs/1904.05712v1
PDF	http://arxiv.org/pdf/1904.05712v1.pdf
PWC	https://paperswithcode.com/paper/reconstructing-network-inputs-with-additive
Repo
Framework

3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion


Title	3D Reconstruction of Whole Stomach from Endoscope Video Using Structure-from-Motion
Authors	Aji Resindra Widya, Yusuke Monno, Kosuke Imahori, Masatoshi Okutomi, Sho Suzuki, Takuji Gotoda, Kenji Miki
Abstract	Gastric endoscopy is a common clinical practice that enables medical doctors to diagnose the stomach inside a body. In order to identify a gastric lesion’s location such as early gastric cancer within the stomach, this work addressed to reconstruct the 3D shape of a whole stomach with color texture information generated from a standard monocular endoscope video. Previous works have tried to reconstruct the 3D structures of various organs from endoscope images. However, they are mainly focused on a partial surface. In this work, we investigated how to enable structure-from-motion (SfM) to reconstruct the whole shape of a stomach from a standard endoscope video. We specifically investigated the combined effect of chromo-endoscopy and color channel selection on SfM. Our study found that 3D reconstruction of the whole stomach can be achieved by using red channel images captured under chromo-endoscopy by spreading indigo carmine (IC) dye on the stomach surface.
Tasks	3D Reconstruction
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12988v1
PDF	https://arxiv.org/pdf/1905.12988v1.pdf
PWC	https://paperswithcode.com/paper/3d-reconstruction-of-whole-stomach-from
Repo
Framework

Semi-supervised Learning of Fetal Anatomy from Ultrasound


Title	Semi-supervised Learning of Fetal Anatomy from Ultrasound
Authors	Jeremy Tan, Anselm Au, Qingjie Meng, Bernhard Kainz
Abstract	Semi-supervised learning methods have achieved excellent performance on standard benchmark datasets using very few labelled images. Anatomy classification in fetal 2D ultrasound is an ideal problem setting to test whether these results translate to non-ideal data. Our results indicate that inclusion of a challenging background class can be detrimental and that semi-supervised learning mostly benefits classes that are already distinct, sometimes at the expense of more similar classes.
Tasks
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11624v1
PDF	https://arxiv.org/pdf/1908.11624v1.pdf
PWC	https://paperswithcode.com/paper/semi-supervised-learning-of-fetal-anatomy
Repo
Framework

Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry


Title	Offset Sampling Improves Deep Learning based Accelerated MRI Reconstructions by Exploiting Symmetry
Authors	Aaron Defazio
Abstract	Deep learning approaches to accelerated MRI take a matrix of sampled Fourier-space lines as input and produce a spatial image as output. In this work we show that by careful choice of the offset used in the sampling procedure, the symmetries in k-space can be better exploited, producing higher quality reconstructions than given by standard equally-spaced samples or randomized samples motivated by compressed sensing.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.01101v2
PDF	https://arxiv.org/pdf/1912.01101v2.pdf
PWC	https://paperswithcode.com/paper/offset-masking-improves-deep-learning-based
Repo
Framework

Variable Neighborhood Search for the Bin Packing Problem with Compatible Categories


Title	Variable Neighborhood Search for the Bin Packing Problem with Compatible Categories
Authors	Luiz F. O. Moura Santos, Hugo T. Y. Yoshizaki, Claudio B. Cunha
Abstract	Bin Packing with Conflicts (BPC) are problems in which items with compatibility constraints must be packed in the least number of bins, not exceeding the capacity of the bins and ensuring that non-conflicting items are packed in each bin. In this work, we introduce the Bin Packing Problem with Compatible Categories (BPCC), a variant of the BPC in which items belong to conflicting or compatible categories, in opposition to the item-by-item incompatibility found in previous literature. It is a common problem in the context of last mile distribution to nanostores located in densely populated areas. To efficiently solve real-life sized instances of the problem, we propose a Variable Neighborhood Search (VNS) metaheuristic algorithm. Computational experiments suggest that the algorithm yields good solutions in very short times while compared to linear integer programming running on a high-performance computing environment.
Tasks
Published	2019-05-09
URL	https://arxiv.org/abs/1905.03427v1
PDF	https://arxiv.org/pdf/1905.03427v1.pdf
PWC	https://paperswithcode.com/paper/190503427
Repo
Framework

Evaluating CNNs on the Gestalt Principle of Closure


Title	Evaluating CNNs on the Gestalt Principle of Closure
Authors	Gregor Ehrensperger, Sebastian Stabinger, Antonio Rodríguez Sánchez
Abstract	Deep convolutional neural networks (CNNs) are widely known for their outstanding performance in classification and regression tasks over high-dimensional data. This made them a popular and powerful tool for a large variety of applications in industry and academia. Recent publications show that seemingly easy classifaction tasks (for humans) can be very challenging for state of the art CNNs. An attempt to describe how humans perceive visual elements is given by the Gestalt principles. In this paper we evaluate AlexNet and GoogLeNet regarding their performance on classifying the correctness of the well known Kanizsa triangles, which heavily rely on the Gestalt principle of closure. Therefore we created various datasets containing valid as well as invalid variants of the Kanizsa triangle. Our findings suggest that perceiving objects by utilizing the principle of closure is very challenging for the applied network architectures but they appear to adapt to the effect of closure.
Tasks
Published	2019-03-30
URL	http://arxiv.org/abs/1904.00285v1
PDF	http://arxiv.org/pdf/1904.00285v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-cnns-on-the-gestalt-principle-of
Repo
Framework

RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies


Title	RL-Based Method for Benchmarking the Adversarial Resilience and Robustness of Deep Reinforcement Learning Policies
Authors	Vahid Behzadan, William Hsu
Abstract	This paper investigates the resilience and robustness of Deep Reinforcement Learning (DRL) policies to adversarial perturbations in the state space. We first present an approach for the disentanglement of vulnerabilities caused by representation learning of DRL agents from those that stem from the sensitivity of the DRL policies to distributional shifts in state transitions. Building on this approach, we propose two RL-based techniques for quantitative benchmarking of adversarial resilience and robustness in DRL policies against perturbations of state transitions. We demonstrate the feasibility of our proposals through experimental evaluation of resilience and robustness in DQN, A2C, and PPO2 policies trained in the Cartpole environment.
Tasks	Representation Learning
Published	2019-06-03
URL	https://arxiv.org/abs/1906.01110v1
PDF	https://arxiv.org/pdf/1906.01110v1.pdf
PWC	https://paperswithcode.com/paper/rl-based-method-for-benchmarking-the
Repo
Framework

Incremental Concept Learning via Online Generative Memory Recall


Title	Incremental Concept Learning via Online Generative Memory Recall
Authors	Huaiyu Li, Weiming Dong, Bao-Gang Hu
Abstract	The ability to learn more and more concepts over time from incrementally arriving data is essential for the development of a life-long learning system. However, deep neural networks often suffer from forgetting previously learned concepts when continually learning new concepts, which is known as catastrophic forgetting problem. The main reason for catastrophic forgetting is that the past concept data is not available and neural weights are changed during incrementally learning new concepts. In this paper, we propose a pseudo-rehearsal based class incremental learning approach to make neural networks capable of continually learning new concepts. We use a conditional generative adversarial network to consolidate old concepts memory and recall pseudo samples during learning new concepts and a balanced online memory recall strategy is to maximally maintain old memories. And we design a comprehensible incremental concept learning network as well as a concept contrastive loss to alleviate the magnitude of neural weights change. We evaluate the proposed approach on MNIST, Fashion-MNIST and SVHN datasets and compare with other rehearsal based approaches. The extensive experiments demonstrate the effectiveness of our approach.
Tasks
Published	2019-07-05
URL	https://arxiv.org/abs/1907.02788v1
PDF	https://arxiv.org/pdf/1907.02788v1.pdf
PWC	https://paperswithcode.com/paper/incremental-concept-learning-via-online
Repo
Framework

A Reproducing Kernel Hilbert Space log-rank test for the two-sample problem


Title	A Reproducing Kernel Hilbert Space log-rank test for the two-sample problem
Authors	Tamara Fernandez, Nicolas Rivera
Abstract	Weighted log-rank tests are arguably the most widely used tests by practitioners for the two-sample problem in the context of right-censored data. Many approaches have been considered to make weighted log-rank tests more robust against a broader family of alternatives, among them: considering linear combinations of weighted log-rank tests or taking the maximum between a finite collection of them. In this paper, we propose as test-statistic the supremum of a collection of (potentially infinite) weight-indexed log-rank tests where the index space is the unit ball of a reproducing kernel Hilbert space (RKHS). By using the good properties of the RKHS’s we provide an exact and simple evaluation of the test-statistic and establish relationships between previous tests in the literature. Additionally, we show that for a special family of RKHS’s, the proposed test is omnibus. We finalise by performing an empirical evaluation of the proposed methodology and show an application to a real data scenario.
Tasks
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05187v1
PDF	http://arxiv.org/pdf/1904.05187v1.pdf
PWC	https://paperswithcode.com/paper/a-reproducing-kernel-hilbert-space-log-rank
Repo
Framework

Simultaneous Region Localization and Hash Coding for Fine-grained Image Retrieval


Title	Simultaneous Region Localization and Hash Coding for Fine-grained Image Retrieval
Authors	Haien Zeng, Hanjiang Lai, Jian Yin
Abstract	Fine-grained image hashing is a challenging problem due to the difficulties of discriminative region localization and hash code generation. Most existing deep hashing approaches solve the two tasks independently. While these two tasks are correlated and can reinforce each other. In this paper, we propose a deep fine-grained hashing to simultaneously localize the discriminative regions and generate the efficient binary codes. The proposed approach consists of a region localization module and a hash coding module. The region localization module aims to provide informative regions to the hash coding module. The hash coding module aims to generate effective binary codes and give feedback for learning better localizer. Moreover, to better capture subtle differences, multi-scale regions at different layers are learned without the need of bounding-box/part annotations. Extensive experiments are conducted on two public benchmark fine-grained datasets. The results demonstrate significant improvements in the performance of our method relative to other fine-grained hashing algorithms.
Tasks	Code Generation, Image Retrieval
Published	2019-11-19
URL	https://arxiv.org/abs/1911.08028v1
PDF	https://arxiv.org/pdf/1911.08028v1.pdf
PWC	https://paperswithcode.com/paper/simultaneous-region-localization-and-hash
Repo
Framework

Non-Determinism in Neural Networks for Adversarial Robustness


Title	Non-Determinism in Neural Networks for Adversarial Robustness
Authors	Daanish Ali Khan, Linhong Li, Ninghao Sha, Zhuoran Liu, Abelino Jimenez, Bhiksha Raj, Rita Singh
Abstract	Recent breakthroughs in the field of deep learning have led to advancements in a broad spectrum of tasks in computer vision, audio processing, natural language processing and other areas. In most instances where these tasks are deployed in real-world scenarios, the models used in them have been shown to be susceptible to adversarial attacks, making it imperative for us to address the challenge of their adversarial robustness. Existing techniques for adversarial robustness fall into three broad categories: defensive distillation techniques, adversarial training techniques, and randomized or non-deterministic model based techniques. In this paper, we propose a novel neural network paradigm that falls under the category of randomized models for adversarial robustness, but differs from all existing techniques under this category in that it models each parameter of the network as a statistical distribution with learnable parameters. We show experimentally that this framework is highly robust to a variety of white-box and black-box adversarial attacks, while preserving the task-specific performance of the traditional neural network model.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10906v1
PDF	https://arxiv.org/pdf/1905.10906v1.pdf
PWC	https://paperswithcode.com/paper/non-determinism-in-neural-networks-for
Repo
Framework

Fairness in Multi-agent Reinforcement Learning for Stock Trading


Title	Fairness in Multi-agent Reinforcement Learning for Stock Trading
Authors	Wenhang Bao
Abstract	Unfair stock trading strategies have been shown to be one of the most negative perceptions that customers can have concerning trading and may result in long-term losses for a company. Investment banks usually place trading orders for multiple clients with the same target assets but different order sizes and diverse requirements such as time frame and risk aversion level, thereby total earning and individual earning cannot be optimized at the same time. Orders executed earlier would affect the market price level, so late execution usually means additional implementation cost. In this paper, we propose a novel scheme that utilizes multi-agent reinforcement learning systems to derive stock trading strategies for all clients which keep a balance between revenue and fairness. First, we demonstrate that Reinforcement learning (RL) is able to learn from experience and adapt the trading strategies to the complex market environment. Secondly, we show that the Multi-agent RL system allows developing trading strategies for all clients individually, thus optimizing individual revenue. Thirdly, we use the Generalized Gini Index (GGI) aggregation function to control the fairness level of the revenue across all clients. Lastly, we empirically demonstrate the superiority of the novel scheme in improving fairness meanwhile maintaining optimization of revenue.
Tasks	Multi-agent Reinforcement Learning
Published	2019-12-14
URL	https://arxiv.org/abs/2001.00918v1
PDF	https://arxiv.org/pdf/2001.00918v1.pdf
PWC	https://paperswithcode.com/paper/fairness-in-multi-agent-reinforcement
Repo
Framework

Team JL Solution to Google Landmark Recognition 2019


Title	Team JL Solution to Google Landmark Recognition 2019
Authors	Yinzheng Gu, Chuanpeng Li
Abstract	In this paper, we describe our solution to the Google Landmark Recognition 2019 Challenge held on Kaggle. Due to the large number of classes, noisy data, imbalanced class sizes, and the presence of a significant amount of distractors in the test set, our method is based mainly on retrieval techniques with both global and local CNN approaches. Our full pipeline, after ensembling the models and applying several steps of re-ranking strategies, scores 0.37606 GAP on the private leaderboard which won the 1st place in the competition.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.11874v1
PDF	https://arxiv.org/pdf/1906.11874v1.pdf
PWC	https://paperswithcode.com/paper/team-jl-solution-to-google-landmark
Repo
Framework

Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning


Title	Intelligent Coordination among Multiple Traffic Intersections Using Multi-Agent Reinforcement Learning
Authors	Ujwal Padam Tewari, Vishal Bidawatka, Varsha Raveendran, Vinay Sudhakaran
Abstract	We use Asynchronous Advantage Actor Critic (A3C) for implementing an AI agent in the controllers that optimize flow of traffic across a single intersection and then extend it to multiple intersections by considering a multi-agent setting. We explore three different methodologies to address the multi-agent problem - (1) use of asynchronous property of A3C to control multiple intersections using a single agent (2) utilise self/competitive play among independent agents across multiple intersections and (3) ingest a global reward function among agents to introduce cooperative behavior between intersections. We observe that (1) & (2) leads to a reduction in traffic congestion. Additionally the use of (3) with (1) & (2) led to a further reduction in congestion.
Tasks	Multi-agent Reinforcement Learning
Published	2019-12-09
URL	https://arxiv.org/abs/1912.03851v1
PDF	https://arxiv.org/pdf/1912.03851v1.pdf
PWC	https://paperswithcode.com/paper/intelligent-coordination-among-multiple
Repo
Framework

Deep Learning in Cardiology


Title	Deep Learning in Cardiology
Authors	Paschalis Bizopoulos, Dimitrios Koutsouris
Abstract	The medical field is creating large amount of data that physicians are unable to decipher and use efficiently. Moreover, rule-based expert systems are inefficient in solving complicated medical tasks or for creating insights using big data. Deep learning has emerged as a more accurate and effective technology in a wide range of medical problems such as diagnosis, prediction and intervention. Deep learning is a representation learning method that consists of layers that transform the data non-linearly, thus, revealing hierarchical relationships and structures. In this review we survey deep learning application papers that use structured data, signal and imaging modalities from cardiology. We discuss the advantages and limitations of applying deep learning in cardiology that also apply in medicine in general, while proposing certain directions as the most viable for clinical use.
Tasks	Representation Learning
Published	2019-02-22
URL	http://arxiv.org/abs/1902.11122v1
PDF	http://arxiv.org/pdf/1902.11122v1.pdf
PWC	https://paperswithcode.com/paper/deep-learning-in-cardiology
Repo
Framework