January 27, 2020

2914 words 14 mins read

Paper Group ANR 1087

Adversarial VC-dimension and Sample Complexity of Neural Networks. Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net. Quantum algorithm for finding the negative curvature direction in non-convex optimization. MDS-Net: A Model-Driven Stack-Based Fully Convolutional Network for Pancreas Segmentation. Prospection: Interpretable …

Adversarial VC-dimension and Sample Complexity of Neural Networks


Title	Adversarial VC-dimension and Sample Complexity of Neural Networks
Authors	Zetong Qi, T. J. Wilder
Abstract	Adversarial attacks during the testing phase of neural networks pose a challenge for the deployment of neural networks in security critical settings. These attacks can be performed by adding noise that is imperceptible to humans on top of the original data. By doing so, an attacker can create an adversarial sample, which will cause neural networks to misclassify. In this paper, we seek to understand the theoretical limits of what can be learned by neural networks in the presence of an adversary. We first defined the hypothesis space of a neural network, and showed the relationship between the growth number of the entire neural network and the growth number of each neuron. Combine that with the adversarial Vapnik-Chervonenkis(VC)-dimension of halfspace classifiers, we concluded the adversarial VC-dimension of the neural networks with sign activation functions.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.08865v1
PDF	https://arxiv.org/pdf/1912.08865v1.pdf
PWC	https://paperswithcode.com/paper/adversarial-vc-dimension-and-sample
Repo
Framework

Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net


Title	Deep Q Learning Driven CT Pancreas Segmentation with Geometry-Aware U-Net
Authors	Yunze Man, Yangsibo Huang, Junyi Feng, Xi Li, Fei Wu
Abstract	Segmentation 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 with deformable U-Net to accurately segment the pancreas by explicitly interacting with contextual information and extract anisotropic features from pancreas. The DQN based model learns a context-adaptive localization policy to produce a visually tightened and precise localization bounding box of the pancreas. Furthermore, deformable U-Net captures geometry-aware information of pancreas by learning geometrically deformable filters for feature extraction. Experiments on NIH dataset validate the effectiveness of the proposed framework in pancreas segmentation.
Tasks	Pancreas Segmentation, Q-Learning
Published	2019-04-19
URL	http://arxiv.org/abs/1904.09120v1
PDF	http://arxiv.org/pdf/1904.09120v1.pdf
PWC	https://paperswithcode.com/paper/deep-q-learning-driven-ct-pancreas
Repo
Framework

Quantum algorithm for finding the negative curvature direction in non-convex optimization


Title	Quantum algorithm for finding the negative curvature direction in non-convex optimization
Authors	Kaining Zhang, Min-Hsiu Hsieh, Liu Liu, Dacheng Tao
Abstract	We present an efficient quantum algorithm aiming to find the negative curvature direction for escaping the saddle point, which is the critical subroutine for many second-order non-convex optimization algorithms. We prove that our algorithm could produce the target state corresponding to the negative curvature direction with query complexity O(polylog(d) /{\epsilon}), where d is the dimension of the optimization function. The quantum negative curvature finding algorithm is exponentially faster than any known classical method which takes time at least O(d /\sqrt{\epsilon}). Moreover, we propose an efficient quantum algorithm to achieve the classical read-out of the target state. Our classical read-out algorithm runs exponentially faster on the degree of d than existing counterparts.
Tasks
Published	2019-09-17
URL	https://arxiv.org/abs/1909.07622v1
PDF	https://arxiv.org/pdf/1909.07622v1.pdf
PWC	https://paperswithcode.com/paper/quantum-algorithm-for-finding-the-negative
Repo
Framework

MDS-Net: A Model-Driven Stack-Based Fully Convolutional Network for Pancreas Segmentation


Title	MDS-Net: A Model-Driven Stack-Based Fully Convolutional Network for Pancreas Segmentation
Authors	Hao Li, Jun Li, Xiaozhu Lin, Xiaohua Qian
Abstract	The irregular geometry and high inter-slice variability in computerized tomography (CT) scans of the human pancreas make an accurate segmentation of this crucial organ a challenging task for existing data-driven deep learning methods. To address this problem, we present a novel model-driven stack-based fully convolutional network with a bi-directional convolutional long short-term memory network for pancreas segmentation, termed MDS-Net. The MDS-Net’s cost function includes data approximation term and prior knowledge regularization term combined with a stack scheme for capturing and fusing the two-dimensional (2D) and local three-dimensional (3D) context information. Specifically, 3D CT scans are divided into multiple stacks, and each multi-slice stack is used as a basic unit for network training and modeling of the local spatial context. To highlight the importance of single slices in segmentation, the inter-slice relationships in the stack data are also incorporated in the MDS-Net framework. For implementing this proposed model-driven method, we create a stack-based U-Net architecture and successfully derive its back-propagation procedure for end-to-end training. Furthermore, a bi-directional convolutional long short-term memory (BiCLSTM) network is utilized to integrate upper and lower slice information, thereby ensuring the consistency of adjacent CT slices and intra-stack. Finally, extensive quantitative assessments on the NIH Pancreas-CT dataset demonstrated higher pancreatic segmentation accuracy and reliability of MDS-Net compared to other state-of-the-art methods.
Tasks	Pancreas Segmentation
Published	2019-03-03
URL	https://arxiv.org/abs/1903.00832v2
PDF	https://arxiv.org/pdf/1903.00832v2.pdf
PWC	https://paperswithcode.com/paper/pancreas-segmentation-via-spatial-context
Repo
Framework

Prospection: Interpretable Plans From Language By Predicting the Future


Title	Prospection: Interpretable Plans From Language By Predicting the Future
Authors	Chris Paxton, Yonatan Bisk, Jesse Thomason, Arunkumar Byravan, Dieter Fox
Abstract	High-level human instructions often correspond to behaviors with multiple implicit steps. In order for robots to be useful in the real world, they must be able to to reason over both motions and intermediate goals implied by human instructions. In this work, we propose a framework for learning representations that convert from a natural-language command to a sequence of intermediate goals for execution on a robot. A key feature of this framework is prospection, training an agent not just to correctly execute the prescribed command, but to predict a horizon of consequences of an action before taking it. We demonstrate the fidelity of plans generated by our framework when interpreting real, crowd-sourced natural language commands for a robot in simulated scenes.
Tasks
Published	2019-03-20
URL	http://arxiv.org/abs/1903.08309v1
PDF	http://arxiv.org/pdf/1903.08309v1.pdf
PWC	https://paperswithcode.com/paper/prospection-interpretable-plans-from-language
Repo
Framework

Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models


Title	Wavelets to the Rescue: Improving Sample Quality of Latent Variable Deep Generative Models
Authors	Prashnna K Gyawali, Rudra Shah, Linwei Wang, VSR Veeravasarapu, Maneesh Singh
Abstract	Variational Autoencoders (VAE) are probabilistic deep generative models underpinned by elegant theory, stable training processes, and meaningful manifold representations. However, they produce blurry images due to a lack of explicit emphasis over high-frequency textural details of the images, and the difficulty to directly model the complex joint probability distribution over the high-dimensional image space. In this work, we approach these two challenges with a novel wavelet space VAE that uses the decoder to model the images in the wavelet coefficient space. This enables the VAE to emphasize over high-frequency components within an image obtained via wavelet decomposition. Additionally, by decomposing the complex function of generating high-dimensional images into inverse wavelet transformation and generation of wavelet coefficients, the latter becomes simpler to model by the VAE. We empirically validate that deep generative models operating in the wavelet space can generate images of higher quality than the image (RGB) space counterparts. Quantitatively, on benchmark natural image datasets, we achieve consistently better FID scores than VAE based architectures and competitive FID scores with a variety of GAN models for the same architectural and experimental setup. Furthermore, the proposed wavelet-based generative model retains desirable attributes like disentangled and informative latent representation without losing the quality in the generated samples.
Tasks
Published	2019-10-26
URL	https://arxiv.org/abs/1911.05627v1
PDF	https://arxiv.org/pdf/1911.05627v1.pdf
PWC	https://paperswithcode.com/paper/wavelets-to-the-rescue-improving-sample
Repo
Framework

Comparison of Hand-held WEMI Target Detection Algorithms


Title	Comparison of Hand-held WEMI Target Detection Algorithms
Authors	Connor H. McCurley, James Bocinsky, Alina Zare
Abstract	Wide-band Electromagnetic Induction Sensors (WEMI) have been used for a number of years in subsurface detection of explosive hazards. While WEMI sensors have proven effective at localizing objects exhibiting large magnetic responses, detecting objects lacking or containing very low amounts of conductive materials can be challenging. In this paper, we compare a number of target detection algorithms in the literature in terms of detection performance. In the comparison, methods are tested on two real-world data sets: one containing relatively low amounts of ground noise pollution, and the other demonstrating highly-magnetic soil interference. Results are quantitatively evaluated through receiver-operator characteristic (ROC) curves and are used to highlight the strengths and weaknesses of the compared approaches in hand-held explosive hazard detection.
Tasks
Published	2019-03-22
URL	http://arxiv.org/abs/1903.09587v1
PDF	http://arxiv.org/pdf/1903.09587v1.pdf
PWC	https://paperswithcode.com/paper/comparison-of-hand-held-wemi-target-detection
Repo
Framework

Skeleton-Based Hand Gesture Recognition by Learning SPD Matrices with Neural Networks


Title	Skeleton-Based Hand Gesture Recognition by Learning SPD Matrices with Neural Networks
Authors	Xuan Nguyen, Luc Brun, Olivier Lezoray, Sébastien Bougleux
Abstract	In this paper, we propose a new hand gesture recognition method based on skeletal data by learning SPD matrices with neural networks. We model the hand skeleton as a graph and introduce a neural network for SPD matrix learning, taking as input the 3D coordinates of hand joints. The proposed network is based on two newly designed layers that transform a set of SPD matrices into a SPD matrix. For gesture recognition, we train a linear SVM classifier using features extracted from our network. Experimental results on a challenging dataset (Dynamic Hand Gesture dataset from the SHREC 2017 3D Shape Retrieval Contest) show that the proposed method outperforms state-of-the-art methods.
Tasks	3D Shape Retrieval, Gesture Recognition, Hand Gesture Recognition, Hand-Gesture Recognition
Published	2019-05-20
URL	https://arxiv.org/abs/1905.07917v1
PDF	https://arxiv.org/pdf/1905.07917v1.pdf
PWC	https://paperswithcode.com/paper/skeleton-based-hand-gesture-recognition-by
Repo
Framework

Online Vehicle Trajectory Prediction using Policy Anticipation Network and Optimization-based Context Reasoning


Title	Online Vehicle Trajectory Prediction using Policy Anticipation Network and Optimization-based Context Reasoning
Authors	Wenchao Ding, Shaojie Shen
Abstract	In this paper, we present an online two-level vehicle trajectory prediction framework for urban autonomous driving where there are complex contextual factors, such as lane geometries, road constructions, traffic regulations and moving agents. Our method combines high-level policy anticipation with low-level context reasoning. We leverage a long short-term memory (LSTM) network to anticipate the vehicle’s driving policy (e.g., forward, yield, turn left, turn right, etc.) using its sequential history observations. The policy is then used to guide a low-level optimization-based context reasoning process. We show that it is essential to incorporate the prior policy anticipation due to the multimodal nature of the future trajectory. Moreover, contrary to existing regression-based trajectory prediction methods, our optimization-based reasoning process can cope with complex contextual factors. The final output of the two-level reasoning process is a continuous trajectory that automatically adapts to different traffic configurations and accurately predicts future vehicle motions. The performance of the proposed framework is analyzed and validated in an emerging autonomous driving simulation platform (CARLA).
Tasks	Autonomous Driving, Trajectory Prediction
Published	2019-03-03
URL	http://arxiv.org/abs/1903.00847v1
PDF	http://arxiv.org/pdf/1903.00847v1.pdf
PWC	https://paperswithcode.com/paper/online-vehicle-trajectory-prediction-using
Repo
Framework

Individual specialization in multi-task environments with multiagent reinforcement learners


Title	Individual specialization in multi-task environments with multiagent reinforcement learners
Authors	Marco Jerome Gasparrini, Ricard Solé, Martí Sánchez-Fibla
Abstract	There is a growing interest in Multi-Agent Reinforcement Learning (MARL) as the first steps towards building general intelligent agents that learn to make low and high-level decisions in non-stationary complex environments in the presence of other agents. Previous results point us towards increased conditions for coordination, efficiency/fairness, and common-pool resource sharing. We further study coordination in multi-task environments where several rewarding tasks can be performed and thus agents don’t necessarily need to perform well in all tasks, but under certain conditions may specialize. An observation derived from the study is that epsilon greedy exploration of value-based reinforcement learning methods is not adequate for multi-agent independent learners because the epsilon parameter that controls the probability of selecting a random action synchronizes the agents artificially and forces them to have deterministic policies at the same time. By using policy-based methods with independent entropy regularised exploration updates, we achieved a better and smoother convergence. Another result that needs to be further investigated is that with an increased number of agents specialization tends to be more probable.
Tasks	Multi-agent Reinforcement Learning
Published	2019-12-29
URL	https://arxiv.org/abs/1912.12671v1
PDF	https://arxiv.org/pdf/1912.12671v1.pdf
PWC	https://paperswithcode.com/paper/individual-specialization-in-multi-task
Repo
Framework

AnomiGAN: Generative adversarial networks for anonymizing private medical data


Title	AnomiGAN: Generative adversarial networks for anonymizing private medical data
Authors	Ho Bae, Dahuin Jung, Sungroh Yoon
Abstract	Typical personal medical data contains sensitive information about individuals. Storing or sharing the personal medical data is thus often risky. For example, a short DNA sequence can provide information that can not only identify an individual, but also his or her relatives. Nonetheless, most countries and researchers agree on the necessity of collecting personal medical data. This stems from the fact that medical data, including genomic data, are an indispensable resource for further research and development regarding disease prevention and treatment. To prevent personal medical data from being misused, techniques to reliably preserve sensitive information should be developed for real world application. In this paper, we propose a framework called anonymized generative adversarial networks (AnomiGAN), to improve the maintenance of privacy of personal medical data, while also maintaining high prediction performance. We compared our method to state-of-the-art techniques and observed that our method preserves the same level of privacy as differential privacy (DP), but had better prediction results. We also observed that there is a trade-off between privacy and performance results depending on the degree of preservation of the original data. Here, we provide a mathematical overview of our proposed model and demonstrate its validation using UCI machine learning repository datasets in order to highlight its utility in practice. Experimentally, our approach delivers a better performance compared to that of the DP approach.
Tasks
Published	2019-01-31
URL	http://arxiv.org/abs/1901.11313v1
PDF	http://arxiv.org/pdf/1901.11313v1.pdf
PWC	https://paperswithcode.com/paper/anomigan-generative-adversarial-networks-for
Repo
Framework

Learning Concepts Definable in First-Order Logic with Counting


Title	Learning Concepts Definable in First-Order Logic with Counting
Authors	Steffen van Bergerem
Abstract	We study classification problems over relational background structures for hypotheses that are defined using logics with counting. The aim of this paper is to find learning algorithms running in time sublinear in the size of the background structure. We show that hypotheses defined by FOCN(P)-formulas over structures of polylogarithmic degree can be learned in sublinear time. Furthermore, we prove that for structures of unbounded degree there is no sublinear learning algorithm for first-order formulas.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03820v1
PDF	https://arxiv.org/pdf/1909.03820v1.pdf
PWC	https://paperswithcode.com/paper/learning-concepts-definable-in-first-order
Repo
Framework

Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities


Title	Automatic Registration between Cone-Beam CT and Scanned Surface via Deep-Pose Regression Neural Networks and Clustered Similarities
Authors	Minyoung Chung, Jingyu Lee, Wisoo Song, Youngchan Song, Il-Hyung Yang, Jeongjin Lee, Yeong-Gil Shin
Abstract	Computerized registration between maxillofacial cone-beam computed tomography (CT) images and a scanned dental model is an essential prerequisite in surgical planning for dental implants or orthognathic surgery. We propose a novel method that performs fully automatic registration between a cone-beam CT image and an optically scanned model. To build a robust and automatic initial registration method, our method applies deep-pose regression neural networks in a reduced domain (i.e., 2-dimensional image). Subsequently, fine registration is performed via optimal clusters. Majority voting system achieves globally optimal transformations while each cluster attempts to optimize local transformation parameters. The coherency of clusters determines their candidacy for the optimal cluster set. The outlying regions in the iso-surface are effectively removed based on the consensus among the optimal clusters. The accuracy of registration was evaluated by the Euclidean distance of 10 landmarks on a scanned model which were annotated by the experts in the field. The experiments show that the proposed method’s registration accuracy, measured in landmark distance, outperforms other existing methods by 30.77% to 70%. In addition to achieving high accuracy, our proposed method requires neither human-interactions nor priors (e.g., iso-surface extraction). The main significance of our study is twofold: 1) the employment of light-weighted neural networks which indicates the applicability of neural network in extracting pose cues that can be easily obtained and 2) the introduction of an optimal cluster-based registration method that can avoid metal artifacts during the matching procedures.
Tasks	Computed Tomography (CT)
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12250v1
PDF	https://arxiv.org/pdf/1907.12250v1.pdf
PWC	https://paperswithcode.com/paper/automatic-registration-between-cone-beam-ct
Repo
Framework

Interactive Teaching Algorithms for Inverse Reinforcement Learning


Title	Interactive Teaching Algorithms for Inverse Reinforcement Learning
Authors	Parameswaran Kamalaruban, Rati Devidze, Volkan Cevher, Adish Singla
Abstract	We study the problem of inverse reinforcement learning (IRL) with the added twist that the learner is assisted by a helpful teacher. More formally, we tackle the following algorithmic question: How could a teacher provide an informative sequence of demonstrations to an IRL learner to speed up the learning process? We present an interactive teaching framework where a teacher adaptively chooses the next demonstration based on learner’s current policy. In particular, we design teaching algorithms for two concrete settings: an omniscient setting where a teacher has full knowledge about the learner’s dynamics and a blackbox setting where the teacher has minimal knowledge. Then, we study a sequential variant of the popular MCE-IRL learner and prove convergence guarantees of our teaching algorithm in the omniscient setting. Extensive experiments with a car driving simulator environment show that the learning progress can be speeded up drastically as compared to an uninformative teacher.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11867v3
PDF	https://arxiv.org/pdf/1905.11867v3.pdf
PWC	https://paperswithcode.com/paper/interactive-teaching-algorithms-for-inverse
Repo
Framework

Tangent Space Separability in Feedforward Neural Networks


Title	Tangent Space Separability in Feedforward Neural Networks
Authors	Bálint Daróczy, Rita Aleksziev, András Benczúr
Abstract	Hierarchical neural networks are exponentially more efficient than their corresponding “shallow” counterpart with the same expressive power, but involve huge number of parameters and require tedious amounts of training. By approximating the tangent subspace, we suggest a sparse representation that enables switching to shallow networks, GradNet after a very early training stage. Our experiments show that the proposed approximation of the metric improves and sometimes even surpasses the achievable performance of the original network significantly even after a few epochs of training the original feedforward network.
Tasks
Published	2019-12-18
URL	https://arxiv.org/abs/1912.09306v1
PDF	https://arxiv.org/pdf/1912.09306v1.pdf
PWC	https://paperswithcode.com/paper/tangent-space-separability-in-feedforward
Repo
Framework