January 27, 2020

2947 words 14 mins read

Paper Group ANR 1111

Panoptic Edge Detection. Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approach. Adversarial Examples for Edge Detection: They Exist, and They Transfer. Identification of Bugs and Vulnerabilities in TLS Implementation for Windows Operating System Using State Machine Learning. MBCAL: A Simple and Efficient Reinforc …

Panoptic Edge Detection


Title	Panoptic Edge Detection
Authors	Yuan Hu, Yingtian Zou, Jiashi Feng
Abstract	Pursuing more complete and coherent scene understanding towards realistic vision applications drives edge detection from category-agnostic to category-aware semantic level. However, finer delineation of instance-level boundaries still remains unexcavated. In this work, we address a new finer-grained task, termed panoptic edge detection (PED), which aims at predicting semantic-level boundaries for stuff categories and instance-level boundaries for instance categories, in order to provide more comprehensive and unified scene understanding from the perspective of edges.We then propose a versatile framework, Panoptic Edge Network (PEN), which aggregates different tasks of object detection, semantic and instance edge detection into a single holistic network with multiple branches. Based on the same feature representation, the semantic edge branch produces semantic-level boundaries for all categories and the object detection branch generates instance proposals. Conditioned on the prior information from these two branches, the instance edge branch aims at instantiating edge predictions for instance categories. Besides, we also devise a Panoptic Dual F-measure (F2) metric for the new PED task to uniformly measure edge prediction quality for both stuff and instances. By joint end-to-end training, the proposed PEN framework outperforms all competitive baselines on Cityscapes and ADE20K datasets.
Tasks	Edge Detection, Object Detection, Scene Understanding
Published	2019-06-03
URL	https://arxiv.org/abs/1906.00590v1
PDF	https://arxiv.org/pdf/1906.00590v1.pdf
PWC	https://paperswithcode.com/paper/190600590
Repo
Framework

Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approach


Title	Distributed Linear Model Clustering over Networks: A Tree-Based Fused-Lasso ADMM Approach
Authors	Xin Zhang, Jia Liu, Zhengyuan Zhu
Abstract	In this work, we consider to improve the model estimation efficiency by aggregating the neighbors’ information as well as identify the subgroup membership for each node in the network. A tree-based $l_1$ penalty is proposed to save the computation and communication cost. We design a decentralized generalized alternating direction method of multiplier algorithm for solving the objective function in parallel. The theoretical properties are derived to guarantee both the model consistency and the algorithm convergence. Thorough numerical experiments are also conducted to back up our theory, which also show that our approach outperforms in the aspects of the estimation accuracy, computation speed and communication cost.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11549v1
PDF	https://arxiv.org/pdf/1905.11549v1.pdf
PWC	https://paperswithcode.com/paper/distributed-linear-model-clustering-over
Repo
Framework

Adversarial Examples for Edge Detection: They Exist, and They Transfer


Title	Adversarial Examples for Edge Detection: They Exist, and They Transfer
Authors	Christian Cosgrove, Alan L. Yuille
Abstract	Convolutional neural networks have recently advanced the state of the art in many tasks including edge and object boundary detection. However, in this paper, we demonstrate that these edge detectors inherit a troubling property of neural networks: they can be fooled by adversarial examples. We show that adding small perturbations to an image causes HED, a CNN-based edge detection model, to fail to locate edges, to detect nonexistent edges, and even to hallucinate arbitrary configurations of edges. More surprisingly, we find that these adversarial examples transfer to other CNN-based vision models. In particular, attacks on edge detection result in significant drops in accuracy in models trained to perform unrelated, high-level tasks like image classification and semantic segmentation. Our code will be made public.
Tasks	Boundary Detection, Edge Detection, Image Classification, Semantic Segmentation
Published	2019-06-02
URL	https://arxiv.org/abs/1906.00335v1
PDF	https://arxiv.org/pdf/1906.00335v1.pdf
PWC	https://paperswithcode.com/paper/190600335
Repo
Framework

Identification of Bugs and Vulnerabilities in TLS Implementation for Windows Operating System Using State Machine Learning


Title	Identification of Bugs and Vulnerabilities in TLS Implementation for Windows Operating System Using State Machine Learning
Authors	Tarun Yadav, Koustav Sadhukhan
Abstract	TLS protocol is an essential part of secure Internet communication. In past, many attacks have been identified on the protocol. Most of these attacks are due to flaws in protocol implementation. The flaws are due to improper design and implementation of program logic by programmers. One of the widely used implementation of TLS is SChannel which is used in Windows operating system since its inception. We have used protocol state fuzzing to identify vulnerable and undesired state transitions in the state machine of the protocol for various versions of SChannel. The client as well as server components have been analyzed thoroughly using this technique and various flaws have been discovered in the implementation. Exploitation of these flaws under specific circumstances may lead to serious attacks which could disrupt secure communication. In this paper, we analyze state machine models of TLS protocol implementation of SChannel library and describe weaknesses and design flaws in these models, found using protocol state fuzzing.
Tasks
Published	2019-02-20
URL	http://arxiv.org/abs/1902.07471v1
PDF	http://arxiv.org/pdf/1902.07471v1.pdf
PWC	https://paperswithcode.com/paper/identification-of-bugs-and-vulnerabilities-in
Repo
Framework

MBCAL: A Simple and Efficient Reinforcement Learning Method for Recommendation Systems


Title	MBCAL: A Simple and Efficient Reinforcement Learning Method for Recommendation Systems
Authors	Fan Wang, Xiaomin Fang, Lihang Liu, Hao Tian, Zhiming Peng
Abstract	It has been widely regarded that only considering the immediate user feedback is not sufficient for modern industrial recommendation systems. Many previous works attempt to maximize the long term rewards with Reinforcement Learning(RL). However, model-free RL suffers from problems including significant variance in gradient, long convergence period, and requirement of sophisticated online infrastructures. While model-based RL provides a sample-efficient choice, the cost of planning in an online system is unacceptable. To achieve high sample efficiency in practical situations, we propose a novel model-based reinforcement learning method, namely the model-based counterfactual advantage learning(MBCAL). In the proposed method, a masking item is introduced in the environment model learning. With the masking item and the environment model, we introduce the counterfactual future advantage, which eliminates most of the noises in long term rewards. The proposed method selects through approximating the immediate reward and future advantage separately. It is easy to implement, yet it requires reasonable cost in both training and inference processes. In the experiments, we compare our methods with several baselines, including supervised learning, model-free RL, and other model-based RL methods in carefully designed experiments. Results show that our method transcends all the baselines in both sample efficiency and asymptotic performance.
Tasks	Recommendation Systems
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02248v1
PDF	https://arxiv.org/pdf/1911.02248v1.pdf
PWC	https://paperswithcode.com/paper/mbcal-a-simple-and-efficient-reinforcement
Repo
Framework

Yoga-Veganism: Correlation Mining of Twitter Health Data


Title	Yoga-Veganism: Correlation Mining of Twitter Health Data
Authors	Tunazzina Islam
Abstract	Nowadays social media is a huge platform of data. People usually share their interest, thoughts via discussions, tweets, status. It is not possible to go through all the data manually. We need to mine the data to explore hidden patterns or unknown correlations, find out the dominant topic in data and understand people’s interest through the discussions. In this work, we explore Twitter data related to health. We extract the popular topics under different categories (e.g. diet, exercise) discussed in Twitter via topic modeling, observe model behavior on new tweets, discover interesting correlation (i.e. Yoga-Veganism). We evaluate accuracy by comparing with ground truth using manual annotation both for train and test data.
Tasks
Published	2019-06-15
URL	https://arxiv.org/abs/1906.07668v1
PDF	https://arxiv.org/pdf/1906.07668v1.pdf
PWC	https://paperswithcode.com/paper/yoga-veganism-correlation-mining-of-twitter
Repo
Framework

Blink: Fast and Generic Collectives for Distributed ML


Title	Blink: Fast and Generic Collectives for Distributed ML
Authors	Guanhua Wang, Shivaram Venkataraman, Amar Phanishayee, Jorgen Thelin, Nikhil Devanur, Ion Stoica
Abstract	Model parameter synchronization across GPUs introduces high overheads for data-parallel training at scale. Existing parameter synchronization protocols cannot effectively leverage available network resources in the face of ever increasing hardware heterogeneity. To address this, we propose Blink, a collective communication library that dynamically generates optimal communication primitives by packing spanning trees. We propose techniques to minimize the number of trees generated and extend Blink to leverage heterogeneous communication channels for faster data transfers. Evaluations show that compared to the state-of-the-art (NCCL), Blink can achieve up to 8x faster model synchronization, and reduce end-to-end training time for image classification tasks by up to 40%.
Tasks	Image Classification
Published	2019-10-11
URL	https://arxiv.org/abs/1910.04940v1
PDF	https://arxiv.org/pdf/1910.04940v1.pdf
PWC	https://paperswithcode.com/paper/blink-fast-and-generic-collectives-for
Repo
Framework

Unfairness towards subjective opinions in Machine Learning


Title	Unfairness towards subjective opinions in Machine Learning
Authors	Agathe Balayn, Alessandro Bozzon, Zoltan Szlavik
Abstract	Despite the high interest for Machine Learning (ML) in academia and industry, many issues related to the application of ML to real-life problems are yet to be addressed. Here we put forward one limitation which arises from a lack of adaptation of ML models and datasets to specific applications. We formalise a new notion of unfairness as exclusion of opinions. We propose ways to quantify this unfairness, and aid understanding its causes through visualisation. These insights into the functioning of ML-based systems hint at methods to mitigate unfairness.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02455v1
PDF	https://arxiv.org/pdf/1911.02455v1.pdf
PWC	https://paperswithcode.com/paper/unfairness-towards-subjective-opinions-in
Repo
Framework

Artificial Intelligence in Clinical Health Care Applications: Viewpoint


Title	Artificial Intelligence in Clinical Health Care Applications: Viewpoint
Authors	Michael van Hartskamp, Sergio Consoli, Wim Verhaegh, Milan Petković, Anja van de Stolpe
Abstract	The idea of Artificial Intelligence (AI) has a long history. It turned out, however, that reaching intelligence at human levels is more complicated than originally anticipated. Currently we are experiencing a renewed interest in AI, fueled by an enormous increase in computing power and an even larger increase in data, in combination with improved AI technologies like deep learning. Healthcare is considered the next domain to be revolutionized by Artificial Intelligence. While AI approaches are excellently suited to develop certain algorithms, for biomedical applications there are specific challenges. We propose recommendations to improve AI projects in the biomedical space and especially clinical healthcare.
Tasks
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02090v2
PDF	https://arxiv.org/pdf/1906.02090v2.pdf
PWC	https://paperswithcode.com/paper/artificial-intelligence-in-clinical-health
Repo
Framework

Secure Federated Submodel Learning


Title	Secure Federated Submodel Learning
Authors	Chaoyue Niu, Fan Wu, Shaojie Tang, Lifeng Hua, Rongfei Jia, Chengfei Lv, Zhihua Wu, Guihai Chen
Abstract	Federated learning was proposed with an intriguing vision of achieving collaborative machine learning among numerous clients without uploading their private data to a cloud server. However, the conventional framework requires each client to leverage the full model for learning, which can be prohibitively inefficient for resource-constrained clients and large-scale deep learning tasks. We thus propose a new framework, called federated submodel learning, where clients download only the needed parts of the full model, namely submodels, and then upload the submodel updates. Nevertheless, the “position” of a client’s truly required submodel corresponds to her private data, and its disclosure to the cloud server during interactions inevitably breaks the tenet of federated learning. To integrate efficiency and privacy, we have designed a secure federated submodel learning scheme coupled with a private set union protocol as a cornerstone. Our secure scheme features the properties of randomized response, secure aggregation, and Bloom filter, and endows each client with a customized plausible deniability, in terms of local differential privacy, against the position of her desired submodel, thus protecting her private data. We further instantiated our scheme with the e-commerce recommendation scenario in Alibaba, implemented a prototype system, and extensively evaluated its performance over 30-day Taobao user data. The analysis and evaluation results demonstrate the feasibility and scalability of our scheme from model accuracy and convergency, practical communication, computation, and storage overheads, as well as manifest its remarkable advantages over the conventional federated learning framework.
Tasks
Published	2019-11-06
URL	https://arxiv.org/abs/1911.02254v2
PDF	https://arxiv.org/pdf/1911.02254v2.pdf
PWC	https://paperswithcode.com/paper/secure-federated-submodel-learning
Repo
Framework

Adaptive neural network based dynamic surface control for uncertain dual arm robots


Title	Adaptive neural network based dynamic surface control for uncertain dual arm robots
Authors	Dung Tien Pham, Thai Van Nguyen, Hai Xuan Le, Linh Nguyen, Nguyen Huu Thai, Tuan Anh Phan, Hai Tuan Pham, Anh Hoai Duong
Abstract	The paper discusses an adaptive strategy to effectively control nonlinear manipulation motions of a dual arm robot (DAR) under system uncertainties including parameter variations, actuator nonlinearities and external disturbances. It is proposed that the control scheme is first derived from the dynamic surface control (DSC) method, which allows the robot’s end-effectors to robustly track the desired trajectories. Moreover, since exactly determining the DAR system’s dynamics is impractical due to the system uncertainties, the uncertain system parameters are then proposed to be adaptively estimated by the use of the radial basis function network (RBFN). The adaptation mechanism is derived from the Lyapunov theory, which theoretically guarantees stability of the closed-loop control system. The effectiveness of the proposed RBFN-DSC approach is demonstrated by implementing the algorithm in a synthetic environment with realistic parameters, where the obtained results are highly promising.
Tasks
Published	2019-05-08
URL	https://arxiv.org/abs/1905.02914v1
PDF	https://arxiv.org/pdf/1905.02914v1.pdf
PWC	https://paperswithcode.com/paper/adaptive-neural-network-based-dynamic-surface
Repo
Framework

A Convolutional Transformation Network for Malware Classification


Title	A Convolutional Transformation Network for Malware Classification
Authors	Duc-Ly Vu, Trong-Kha Nguyen, Tam V. Nguyen, Tu N. Nguyen, Fabio Massacci, Phu H. Phung
Abstract	Modern malware evolves various detection avoidance techniques to bypass the state-of-the-art detection methods. An emerging trend to deal with this issue is the combination of image transformation and machine learning techniques to classify and detect malware. However, existing works in this field only perform simple image transformation methods that limit the accuracy of the detection. In this paper, we introduce a novel approach to classify malware by using a deep network on images transformed from binary samples. In particular, we first develop a novel hybrid image transformation method to convert binaries into color images that convey the binary semantics. The images are trained by a deep convolutional neural network that later classifies the test inputs into benign or malicious categories. Through the extensive experiments, our proposed method surpasses all baselines and achieves 99.14% in terms of accuracy on the testing set.
Tasks	Malware Classification
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07227v1
PDF	https://arxiv.org/pdf/1909.07227v1.pdf
PWC	https://paperswithcode.com/paper/a-convolutional-transformation-network-for
Repo
Framework

Neural Illumination: Lighting Prediction for Indoor Environments


Title	Neural Illumination: Lighting Prediction for Indoor Environments
Authors	Shuran Song, Thomas Funkhouser
Abstract	This paper addresses the task of estimating the light arriving from all directions to a 3D point observed at a selected pixel in an RGB image. This task is challenging because it requires predicting a mapping from a partial scene observation by a camera to a complete illumination map for a selected position, which depends on the 3D location of the selection, the distribution of unobserved light sources, the occlusions caused by scene geometry, etc. Previous methods attempt to learn this complex mapping directly using a single black-box neural network, which often fails to estimate high-frequency lighting details for scenes with complicated 3D geometry. Instead, we propose “Neural Illumination” a new approach that decomposes illumination prediction into several simpler differentiable sub-tasks: 1) geometry estimation, 2) scene completion, and 3) LDR-to-HDR estimation. The advantage of this approach is that the sub-tasks are relatively easy to learn and can be trained with direct supervision, while the whole pipeline is fully differentiable and can be fine-tuned with end-to-end supervision. Experiments show that our approach performs significantly better quantitatively and qualitatively than prior work.
Tasks
Published	2019-06-18
URL	https://arxiv.org/abs/1906.07370v1
PDF	https://arxiv.org/pdf/1906.07370v1.pdf
PWC	https://paperswithcode.com/paper/neural-illumination-lighting-prediction-for-1
Repo
Framework

FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation


Title	FEAFA: A Well-Annotated Dataset for Facial Expression Analysis and 3D Facial Animation
Authors	Yanfu Yan, Ke Lu, Jian Xue, Pengcheng Gao, Jiayi Lyu
Abstract	Facial expression analysis based on machine learning requires large number of well-annotated data to reflect different changes in facial motion. Publicly available datasets truly help to accelerate research in this area by providing a benchmark resource, but all of these datasets, to the best of our knowledge, are limited to rough annotations for action units, including only their absence, presence, or a five-level intensity according to the Facial Action Coding System. To meet the need for videos labeled in great detail, we present a well-annotated dataset named FEAFA for Facial Expression Analysis and 3D Facial Animation. One hundred and twenty-two participants, including children, young adults and elderly people, were recorded in real-world conditions. In addition, 99,356 frames were manually labeled using Expression Quantitative Tool developed by us to quantify 9 symmetrical FACS action units, 10 asymmetrical (unilateral) FACS action units, 2 symmetrical FACS action descriptors and 2 asymmetrical FACS action descriptors, and each action unit or action descriptor is well-annotated with a floating point number between 0 and 1. To provide a baseline for use in future research, a benchmark for the regression of action unit values based on Convolutional Neural Networks are presented. We also demonstrate the potential of our FEAFA dataset for 3D facial animation. Almost all state-of-the-art algorithms for facial animation are achieved based on 3D face reconstruction. We hence propose a novel method that drives virtual characters only based on action unit value regression of the 2D video frames of source actors.
Tasks	3D Face Reconstruction, Face Reconstruction
Published	2019-04-02
URL	http://arxiv.org/abs/1904.01509v1
PDF	http://arxiv.org/pdf/1904.01509v1.pdf
PWC	https://paperswithcode.com/paper/feafa-a-well-annotated-dataset-for-facial
Repo
Framework

Learning Dense Representations for Entity Retrieval


Title	Learning Dense Representations for Entity Retrieval
Authors	Daniel Gillick, Sayali Kulkarni, Larry Lansing, Alessandro Presta, Jason Baldridge, Eugene Ie, Diego Garcia-Olano
Abstract	We show that it is feasible to perform entity linking by training a dual encoder (two-tower) model that encodes mentions and entities in the same dense vector space, where candidate entities are retrieved by approximate nearest neighbor search. Unlike prior work, this setup does not rely on an alias table followed by a re-ranker, and is thus the first fully learned entity retrieval model. We show that our dual encoder, trained using only anchor-text links in Wikipedia, outperforms discrete alias table and BM25 baselines, and is competitive with the best comparable results on the standard TACKBP-2010 dataset. In addition, it can retrieve candidates extremely fast, and generalizes well to a new dataset derived from Wikinews. On the modeling side, we demonstrate the dramatic value of an unsupervised negative mining algorithm for this task.
Tasks	Entity Linking
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10506v1
PDF	https://arxiv.org/pdf/1909.10506v1.pdf
PWC	https://paperswithcode.com/paper/learning-dense-representations-for-entity
Repo
Framework