April 2, 2020

3201 words 16 mins read

Paper Group ANR 289

Optimizing Correlated Graspability Score and Grasp Regression for Better Grasp Prediction. T-Net: A Template-Supervised Network for Task-specific Feature Extraction in Biomedical Image Analysis. Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning. Batch Stationary Distribution Estimation. The Effect of Data Augmenta …

Optimizing Correlated Graspability Score and Grasp Regression for Better Grasp Prediction


Title	Optimizing Correlated Graspability Score and Grasp Regression for Better Grasp Prediction
Authors	Amaury Depierre, Emmanuel Dellandréa, Liming Chen
Abstract	Grasping objects is one of the most important abilities to master for a robot in order to interact with its environment. Current state-of-the-art methods rely on deep neural networks trained to predict a graspability score jointly but separately from regression of an offset of grasp reference parameters, although the predicted offset could decrease the graspability score. In this paper, we extend a state-of-the-art neural network with a scorer which evaluates the graspability of a given position and introduce a novel loss function which correlates regression of grasp parameters with graspability score. We show that this novel architecture improves the performance from 81.95% for a state-of-the-art grasp detection network to 85.74% on Jacquard dataset. Because real-life applications generally feature scenes of multiple objects laid on a variable decor, we also introduce Jacquard+, a test-only extension of Jacquard dataset. Its role is to complete the traditional real robot evaluation by benchmarking the adaptability of a learned grasp prediction model on a different data distribution than the training one while remaining in totally reproducible conditions. Using this novel benchmark and evaluated through the Simulated Grasp Trial criterion, our proposed model outperforms a state-of-the-art one by 7 points.
Tasks
Published	2020-02-03
URL	https://arxiv.org/abs/2002.00872v1
PDF	https://arxiv.org/pdf/2002.00872v1.pdf
PWC	https://paperswithcode.com/paper/optimizing-correlated-graspability-score-and
Repo
Framework

T-Net: A Template-Supervised Network for Task-specific Feature Extraction in Biomedical Image Analysis


Title	T-Net: A Template-Supervised Network for Task-specific Feature Extraction in Biomedical Image Analysis
Authors	Weinan Song, Yuan Liang, Kun Wang, Lei He
Abstract	Existing deep learning methods depend on an encoder-decoder structure to learn feature representation from the segmentation annotation in biomedical image analysis. However, the effectiveness of feature extraction under this structure decreases due to the indirect optimization process, limited training data size, and simplex supervision method. In this paper, we propose a template-supervised network T-Net for task-specific feature extraction. Specifically, we first obtain templates from pixel-level annotations by down-sampling binary masks of recognition targets according to specific tasks. Then, we directly train the encoding network under the supervision of the derived task-specific templates. Finally, we combine the resulting encoding network with a posterior network for the specific task, e.g. an up-sampling network for segmentation or a region proposal network for detection. Extensive experiments on three public datasets (BraTS-17, MoNuSeg and IDRiD) show that T-Net achieves competitive results to the state-of-the-art methods and superior performance to an encoder-decoder based network. To the best of our knowledge, this is the first in-depth study to improve feature extraction by directly supervise the encoding network and by applying task-specific supervision in biomedical image analysis.
Tasks
Published	2020-02-19
URL	https://arxiv.org/abs/2002.08406v1
PDF	https://arxiv.org/pdf/2002.08406v1.pdf
PWC	https://paperswithcode.com/paper/t-net-a-template-supervised-network-for-task
Repo
Framework

Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning


Title	Lightweight 3D Human Pose Estimation Network Training Using Teacher-Student Learning
Authors	Dong-Hyun Hwang, Suntae Kim, Nicolas Monet, Hideki Koike, Soonmin Bae
Abstract	We present MoVNect, a lightweight deep neural network to capture 3D human pose using a single RGB camera. To improve the overall performance of the model, we apply the teacher-student learning method based knowledge distillation to 3D human pose estimation. Real-time post-processing makes the CNN output yield temporally stable 3D skeletal information, which can be used in applications directly. We implement a 3D avatar application running on mobile in real-time to demonstrate that our network achieves both high accuracy and fast inference time. Extensive evaluations show the advantages of our lightweight model with the proposed training method over previous 3D pose estimation methods on the Human3.6M dataset and mobile devices.
Tasks	3D Human Pose Estimation, 3D Pose Estimation, Pose Estimation
Published	2020-01-15
URL	https://arxiv.org/abs/2001.05097v1
PDF	https://arxiv.org/pdf/2001.05097v1.pdf
PWC	https://paperswithcode.com/paper/lightweight-3d-human-pose-estimation-network
Repo
Framework

Batch Stationary Distribution Estimation


Title	Batch Stationary Distribution Estimation
Authors	Junfeng Wen, Bo Dai, Lihong Li, Dale Schuurmans
Abstract	We consider the problem of approximating the stationary distribution of an ergodic Markov chain given a set of sampled transitions. Classical simulation-based approaches assume access to the underlying process so that trajectories of sufficient length can be gathered to approximate stationary sampling. Instead, we consider an alternative setting where a fixed set of transitions has been collected beforehand, by a separate, possibly unknown procedure. The goal is still to estimate properties of the stationary distribution, but without additional access to the underlying system. We propose a consistent estimator that is based on recovering a correction ratio function over the given data. In particular, we develop a variational power method (VPM) that provides provably consistent estimates under general conditions. In addition to unifying a number of existing approaches from different subfields, we also find that VPM yields significantly better estimates across a range of problems, including queueing, stochastic differential equations, post-processing MCMC, and off-policy evaluation.
Tasks
Published	2020-03-02
URL	https://arxiv.org/abs/2003.00722v1
PDF	https://arxiv.org/pdf/2003.00722v1.pdf
PWC	https://paperswithcode.com/paper/batch-stationary-distribution-estimation
Repo
Framework

The Effect of Data Augmentation on Classification of Atrial Fibrillation in Short Single-Lead ECG Signals Using Deep Neural Networks


Title	The Effect of Data Augmentation on Classification of Atrial Fibrillation in Short Single-Lead ECG Signals Using Deep Neural Networks
Authors	Faezeh Nejati Hatamian, Nishant Ravikumar, Sulaiman Vesal, Felix P. Kemeth, Matthias Struck, Andreas Maier
Abstract	Cardiovascular diseases are the most common cause of mortality worldwide. Detection of atrial fibrillation (AF) in the asymptomatic stage can help prevent strokes. It also improves clinical decision making through the delivery of suitable treatment such as, anticoagulant therapy, in a timely manner. The clinical significance of such early detection of AF in electrocardiogram (ECG) signals has inspired numerous studies in recent years, of which many aim to solve this task by leveraging machine learning algorithms. ECG datasets containing AF samples, however, usually suffer from severe class imbalance, which if unaccounted for, affects the performance of classification algorithms. Data augmentation is a popular solution to tackle this problem. In this study, we investigate the impact of various data augmentation algorithms, e.g., oversampling, Gaussian Mixture Models (GMMs) and Generative Adversarial Networks (GANs), on solving the class imbalance problem. These algorithms are quantitatively and qualitatively evaluated, compared and discussed in detail. The results show that deep learning-based AF signal classification methods benefit more from data augmentation using GANs and GMMs, than oversampling. Furthermore, the GAN results in circa $3%$ better AF classification accuracy in average while performing comparably to the GMM in terms of f1-score.
Tasks	Data Augmentation, Decision Making
Published	2020-02-07
URL	https://arxiv.org/abs/2002.02870v2
PDF	https://arxiv.org/pdf/2002.02870v2.pdf
PWC	https://paperswithcode.com/paper/the-effect-of-data-augmentation-on
Repo
Framework

Discovering Business Area Effects to Process Mining Analysis Using Clustering and Influence Analysis


Title	Discovering Business Area Effects to Process Mining Analysis Using Clustering and Influence Analysis
Authors	Teemu Lehto, Markku Hinkka
Abstract	A common challenge for improving business processes in large organizations is that business people in charge of the operations are lacking a fact-based understanding of the execution details, process variants, and exceptions taking place in business operations. While existing process mining methodologies can discover these details based on event logs, it is challenging to communicate the process mining findings to business people. In this paper, we present a novel methodology for discovering business areas that have a significant effect on the process execution details. Our method uses clustering to group similar cases based on process flow characteristics and then influence analysis for detecting those business areas that correlate most with the discovered clusters. Our analysis serves as a bridge between BPM people and business, people facilitating the knowledge sharing between these groups. We also present an example analysis based on publicly available real-life purchase order process data.
Tasks
Published	2020-03-18
URL	https://arxiv.org/abs/2003.08170v1
PDF	https://arxiv.org/pdf/2003.08170v1.pdf
PWC	https://paperswithcode.com/paper/discovering-business-area-effects-to-process
Repo
Framework

Low-Rank and Total Variation Regularization and Its Application to Image Recovery


Title	Low-Rank and Total Variation Regularization and Its Application to Image Recovery
Authors	Pawan Goyal, Hussam Al Daas, Peter Benner
Abstract	In this paper, we study the problem of image recovery from given partial (corrupted) observations. Recovering an image using a low-rank model has been an active research area in data analysis and machine learning. But often, images are not only of low-rank but they also exhibit sparsity in a transformed space. In this work, we propose a new problem formulation in such a way that we seek to recover an image that is of low-rank and has sparsity in a transformed domain. We further discuss various non-convex non-smooth surrogates of the rank function, leading to a relaxed problem. Then, we present an efficient iterative scheme to solve the relaxed problem that essentially employs the (weighted) singular value thresholding at each iteration. Furthermore, we discuss the convergence properties of the proposed iterative method. We perform extensive experiments, showing that the proposed algorithm outperforms state-of-the-art methodologies in recovering images.
Tasks
Published	2020-03-12
URL	https://arxiv.org/abs/2003.05698v1
PDF	https://arxiv.org/pdf/2003.05698v1.pdf
PWC	https://paperswithcode.com/paper/low-rank-and-total-variation-regularization
Repo
Framework

Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization


Title	Simultaneously Evolving Deep Reinforcement Learning Models using Multifactorial Optimization
Authors	Aritz D. Martinez, Eneko Osaba, Javier Del Ser, Francisco Herrera
Abstract	In recent years, Multifactorial Optimization (MFO) has gained a notable momentum in the research community. MFO is known for its inherent capability to efficiently address multiple optimization tasks at the same time, while transferring information among such tasks to improve their convergence speed. On the other hand, the quantum leap made by Deep Q Learning (DQL) in the Machine Learning field has allowed facing Reinforcement Learning (RL) problems of unprecedented complexity. Unfortunately, complex DQL models usually find it difficult to converge to optimal policies due to the lack of exploration or sparse rewards. In order to overcome these drawbacks, pre-trained models are widely harnessed via Transfer Learning, extrapolating knowledge acquired in a source task to the target task. Besides, meta-heuristic optimization has been shown to reduce the lack of exploration of DQL models. This work proposes a MFO framework capable of simultaneously evolving several DQL models towards solving interrelated RL tasks. Specifically, our proposed framework blends together the benefits of meta-heuristic optimization, Transfer Learning and DQL to automate the process of knowledge transfer and policy learning of distributed RL agents. A thorough experimentation is presented and discussed so as to assess the performance of the framework, its comparison to the traditional methodology for Transfer Learning in terms of convergence, speed and policy quality , and the intertask relationships found and exploited over the search process.
Tasks	Q-Learning, Transfer Learning
Published	2020-02-25
URL	https://arxiv.org/abs/2002.12133v2
PDF	https://arxiv.org/pdf/2002.12133v2.pdf
PWC	https://paperswithcode.com/paper/simultaneously-evolving-deep-reinforcement
Repo
Framework

Generating Semantic Adversarial Examples via Feature Manipulation


Title	Generating Semantic Adversarial Examples via Feature Manipulation
Authors	Shuo Wang, Shangyu Chen, Tianle Chen, Surya Nepal, Carsten Rudolph, Marthie Grobler
Abstract	The vulnerability of deep neural networks to adversarial attacks has been widely demonstrated (e.g., adversarial example attacks). Traditional attacks perform unstructured pixel-wise perturbation to fool the classifier. An alternative approach is to have perturbations in the latent space. However, such perturbations are hard to control due to the lack of interpretability and disentanglement. In this paper, we propose a more practical adversarial attack by designing structured perturbation with semantic meanings. Our proposed technique manipulates the semantic attributes of images via the disentangled latent codes. The intuition behind our technique is that images in similar domains have some commonly shared but theme-independent semantic attributes, e.g. thickness of lines in handwritten digits, that can be bidirectionally mapped to disentangled latent codes. We generate adversarial perturbation by manipulating a single or a combination of these latent codes and propose two unsupervised semantic manipulation approaches: vector-based disentangled representation and feature map-based disentangled representation, in terms of the complexity of the latent codes and smoothness of the reconstructed images. We conduct extensive experimental evaluations on real-world image data to demonstrate the power of our attacks for black-box classifiers. We further demonstrate the existence of a universal, image-agnostic semantic adversarial example.
Tasks	Adversarial Attack
Published	2020-01-06
URL	https://arxiv.org/abs/2001.02297v1
PDF	https://arxiv.org/pdf/2001.02297v1.pdf
PWC	https://paperswithcode.com/paper/generating-semantic-adversarial-examples-via
Repo
Framework

Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentation


Title	Weakly-Supervised Lesion Segmentation on CT Scans using Co-Segmentation
Authors	Vatsal Agarwal, Youbao Tang, Jing Xiao, Ronald M. Summers
Abstract	Lesion segmentation on computed tomography (CT) scans is an important step for precisely monitoring changes in lesion/tumor growth. This task, however, is very challenging since manual segmentation is prohibitively time-consuming, expensive, and requires professional knowledge. Current practices rely on an imprecise substitute called response evaluation criteria in solid tumors (RECIST). Although these markers lack detailed information about the lesion regions, they are commonly found in hospitals’ picture archiving and communication systems (PACS). Thus, these markers have the potential to serve as a powerful source of weak-supervision for 2D lesion segmentation. To approach this problem, this paper proposes a convolutional neural network (CNN) based weakly-supervised lesion segmentation method, which first generates the initial lesion masks from the RECIST measurements and then utilizes co-segmentation to leverage lesion similarities and refine the initial masks. In this work, an attention-based co-segmentation model is adopted due to its ability to learn more discriminative features from a pair of images. Experimental results on the NIH DeepLesion dataset demonstrate that the proposed co-segmentation approach significantly improves lesion segmentation performance, e.g the Dice score increases about 4.0% (from 85.8% to 89.8%).
Tasks	Computed Tomography (CT), Lesion Segmentation
Published	2020-01-23
URL	https://arxiv.org/abs/2001.08590v1
PDF	https://arxiv.org/pdf/2001.08590v1.pdf
PWC	https://paperswithcode.com/paper/weakly-supervised-lesion-segmentation-on-ct
Repo
Framework

Self-Learning AI Framework for Skin Lesion Image Segmentation and Classification


Title	Self-Learning AI Framework for Skin Lesion Image Segmentation and Classification
Authors	Anandhanarayanan Kamalakannan, Shiva Shankar Ganesan, Govindaraj Rajamanickam
Abstract	Image segmentation and classification are the two main fundamental steps in pattern recognition. To perform medical image segmentation or classification with deep learning models, it requires training on large image dataset with annotation. The dermoscopy images (ISIC archive) considered for this work does not have ground truth information for lesion segmentation. Performing manual labelling on this dataset is time-consuming. To overcome this issue, self-learning annotation scheme was proposed in the two-stage deep learning algorithm. The two-stage deep learning algorithm consists of U-Net segmentation model with the annotation scheme and CNN classifier model. The annotation scheme uses a K-means clustering algorithm along with merging conditions to achieve initial labelling information for training the U-Net model. The classifier models namely ResNet-50 and LeNet-5 were trained and tested on the image dataset without segmentation for comparison and with the U-Net segmentation for implementing the proposed self-learning Artificial Intelligence (AI) framework. The classification results of the proposed AI framework achieved training accuracy of 93.8% and testing accuracy of 82.42% when compared with the two classifier models directly trained on the input images.
Tasks	Lesion Segmentation, Medical Image Segmentation, Semantic Segmentation
Published	2020-01-04
URL	https://arxiv.org/abs/2001.05838v1
PDF	https://arxiv.org/pdf/2001.05838v1.pdf
PWC	https://paperswithcode.com/paper/self-learning-ai-framework-for-skin-lesion
Repo
Framework

Distributed Kernel Ridge Regression with Communications


Title	Distributed Kernel Ridge Regression with Communications
Authors	Shao-Bo Lin, Di Wang, Ding-Xuan Zhou
Abstract	This paper focuses on generalization performance analysis for distributed algorithms in the framework of learning theory. Taking distributed kernel ridge regression (DKRR) for example, we succeed in deriving its optimal learning rates in expectation and providing theoretically optimal ranges of the number of local processors. Due to the gap between theory and experiments, we also deduce optimal learning rates for DKRR in probability to essentially reflect the generalization performance and limitations of DKRR. Furthermore, we propose a communication strategy to improve the learning performance of DKRR and demonstrate the power of communications in DKRR via both theoretical assessments and numerical experiments.
Tasks
Published	2020-03-27
URL	https://arxiv.org/abs/2003.12210v1
PDF	https://arxiv.org/pdf/2003.12210v1.pdf
PWC	https://paperswithcode.com/paper/distributed-kernel-ridge-regression-with
Repo
Framework

Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning


Title	Dynamic Sampling and Selective Masking for Communication-Efficient Federated Learning
Authors	Shaoxiong Ji, Wenqi Jiang, Anwar Walid, Xue Li
Abstract	Federated learning (FL) is a novel machine learning setting which enables on-device intelligence via decentralized training and federated optimization. The rapid development of deep neural networks facilitates the learning techniques for modeling complex problems and emerges into federated deep learning under the federated setting. However, the tremendous amount of model parameters burdens the communication network with a high load of transportation. This paper introduces two approaches for improving communication efficiency by dynamic sampling and top-$k$ selective masking. The former controls the fraction of selected client models dynamically, while the latter selects parameters with top-$k$ largest values of difference for federated updating. Experiments on convolutional image classification and recurrent language modeling are conducted on three public datasets to show the effectiveness of our proposed methods.
Tasks	Image Classification, Language Modelling
Published	2020-03-21
URL	https://arxiv.org/abs/2003.09603v1
PDF	https://arxiv.org/pdf/2003.09603v1.pdf
PWC	https://paperswithcode.com/paper/dynamic-sampling-and-selective-masking-for
Repo
Framework

e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation


Title	e-UDA: Efficient Unsupervised Domain Adaptation for Cross-Site Medical Image Segmentation
Authors	Hongwei Li, Timo Loehr, Benedikt Wiestler, Jianguo Zhang, Bjoern Menze
Abstract	Domain adaptation in healthcare data is a potentially critical component in making computer-aided diagnostic systems applicable cross multiple sites and imaging scanners. In this paper, we propose an efficient unsupervised domain adaptation framework for robust image segmentation cross multiple similar domains. We enforce our algorithm to not only adapt to the new domains via an adversarial optimization, rejecting unlikely segmentation patterns, but also to maintain its performance on the source training data, by incorporating both semantic and boundary information into the data distributions. Further, as we do not have labels for the transfer domain, we propose a new quality score for the adaptation process, and strategies to retrain the diagnostic algorithm in a stable fashion. Using multi-centric data from a public benchmark for brain lesion segmentation, we demonstrate that recalibrating on just few unlabeled image sets from the target domain improves segmentation accuracies drastically, with performances almost similar to those from algorithms trained on fresh and fully annotated data from the test domain.
Tasks	Domain Adaptation, Lesion Segmentation, Medical Image Segmentation, Semantic Segmentation, Unsupervised Domain Adaptation
Published	2020-01-25
URL	https://arxiv.org/abs/2001.09313v1
PDF	https://arxiv.org/pdf/2001.09313v1.pdf
PWC	https://paperswithcode.com/paper/e-uda-efficient-unsupervised-domain
Repo
Framework

Two-path Deep Semi-supervised Learning for Timely Fake News Detection


Title	Two-path Deep Semi-supervised Learning for Timely Fake News Detection
Authors	Xishuang Dong, Uboho Victor, Lijun Qian
Abstract	News in social media such as Twitter has been generated in high volume and speed. However, very few of them are labeled (as fake or true news) by professionals in near real time. In order to achieve timely detection of fake news in social media, a novel framework of two-path deep semi-supervised learning is proposed where one path is for supervised learning and the other is for unsupervised learning. The supervised learning path learns on the limited amount of labeled data while the unsupervised learning path is able to learn on a huge amount of unlabeled data. Furthermore, these two paths implemented with convolutional neural networks (CNN) are jointly optimized to complete semi-supervised learning. In addition, we build a shared CNN to extract the low level features on both labeled data and unlabeled data to feed them into these two paths. To verify this framework, we implement a Word CNN based semi-supervised learning model and test it on two datasets, namely, LIAR and PHEME. Experimental results demonstrate that the model built on the proposed framework can recognize fake news effectively with very few labeled data.
Tasks	Fake News Detection
Published	2020-01-31
URL	https://arxiv.org/abs/2002.00763v1
PDF	https://arxiv.org/pdf/2002.00763v1.pdf
PWC	https://paperswithcode.com/paper/two-path-deep-semi-supervised-learning-for
Repo
Framework