January 31, 2020

2831 words 14 mins read

Paper Group ANR 197

Copy-Move Forgery Classification via Unsupervised Domain Adaptation. Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation. Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models. Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting. Towards Optimal Structured CNN …

Copy-Move Forgery Classification via Unsupervised Domain Adaptation


Title	Copy-Move Forgery Classification via Unsupervised Domain Adaptation
Authors	Akash Kumar, Arnav Bhavsar
Abstract	In the current era, image manipulation is becoming increasingly easier, yielding more natural looking images, owing to the modern tools in image processing and computer vision techniques. The task of the segregation of forged images has become very challenging. To tackle such problems, publicly available datasets are insufficient. In this paper, we propose to create a synthetic forged dataset using deep semantic image inpainting algorithm. Furthermore, we use an unsupervised domain adaptation network to detect copy-move forgery in images. Our approach can be helpful in those cases, where the classification of data is unavailable.
Tasks	Domain Adaptation, Image Inpainting, Unsupervised Domain Adaptation
Published	2019-11-14
URL	https://arxiv.org/abs/1911.07932v1
PDF	https://arxiv.org/pdf/1911.07932v1.pdf
PWC	https://paperswithcode.com/paper/copy-move-forgery-classification-via
Repo
Framework

Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation


Title	Hierarchical Point-Edge Interaction Network for Point Cloud Semantic Segmentation
Authors	Li Jiang, Hengshuang Zhao, Shu Liu, Xiaoyong Shen, Chi-Wing Fu, Jiaya Jia
Abstract	We achieve 3D semantic scene labeling by exploring semantic relation between each point and its contextual neighbors through edges. Besides an encoder-decoder branch for predicting point labels, we construct an edge branch to hierarchically integrate point features and generate edge features. To incorporate point features in the edge branch, we establish a hierarchical graph framework, where the graph is initialized from a coarse layer and gradually enriched along the point decoding process. For each edge in the final graph, we predict a label to indicate the semantic consistency of the two connected points to enhance point prediction. At different layers, edge features are also fed into the corresponding point module to integrate contextual information for message passing enhancement in local regions. The two branches interact with each other and cooperate in segmentation. Decent experimental results on several 3D semantic labeling datasets demonstrate the effectiveness of our work.
Tasks	Scene Labeling, Semantic Segmentation
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10469v1
PDF	https://arxiv.org/pdf/1909.10469v1.pdf
PWC	https://paperswithcode.com/paper/190910469
Repo
Framework

Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models


Title	Time to Take Emoji Seriously: They Vastly Improve Casual Conversational Models
Authors	Pieter Delobelle, Bettina Berendt
Abstract	Graphical emoji are ubiquitous in modern-day online conversations. So is a single thumbs-up emoji able to signify an agreement, without any words. We argue that the current state-of-the-art systems are ill-equipped to correctly interpret these emoji, especially in a conversational context. However, in a casual context, the benefits might be high: a better understanding of users’ utterances and more natural, emoji-rich responses. With this in mind, we modify BERT to fully support emoji, both from the Unicode Standard and custom emoji. This modified BERT is then trained on a corpus of question-answer (QA) tuples with a high number of emoji, where we’re able to increase the 1-of-100 accuracy from 12.7% for the current state-of-the-art to 17.8% for our model with emoji support.
Tasks
Published	2019-10-30
URL	https://arxiv.org/abs/1910.13793v1
PDF	https://arxiv.org/pdf/1910.13793v1.pdf
PWC	https://paperswithcode.com/paper/time-to-take-emoji-seriously-they-vastly
Repo
Framework

Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting


Title	Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
Authors	Weiqi Chen, Ling Chen, Yu Xie, Wei Cao, Yusong Gao, Xiaojie Feng
Abstract	Traffic forecasting is of great importance to transportation management and public safety, and very challenging due to the complicated spatial-temporal dependency and essential uncertainty brought about by the road network and traffic conditions. Latest studies mainly focus on modeling the spatial dependency by utilizing graph convolutional networks (GCNs) throughout a fixed weighted graph. However, edges, i.e., the correlations between pair-wise nodes, are much more complicated and interact with each other. In this paper, we propose the Multi-Range Attentive Bicomponent GCN (MRA-BGCN), a novel deep learning model for traffic forecasting. We first build the node-wise graph according to the road network distance and the edge-wise graph according to various edge interaction patterns. Then, we implement the interactions of both nodes and edges using bicomponent graph convolution. The multi-range attention mechanism is introduced to aggregate information in different neighborhood ranges and automatically learn the importance of different ranges. Extensive experiments on two real-world road network traffic datasets, METR-LA and PEMS-BAY, show that our MRA-BGCN achieves the state-of-the-art results.
Tasks
Published	2019-11-27
URL	https://arxiv.org/abs/1911.12093v1
PDF	https://arxiv.org/pdf/1911.12093v1.pdf
PWC	https://paperswithcode.com/paper/multi-range-attentive-bicomponent-graph
Repo
Framework

Towards Optimal Structured CNN Pruning via Generative Adversarial Learning


Title	Towards Optimal Structured CNN Pruning via Generative Adversarial Learning
Authors	Shaohui Lin, Rongrong Ji, Chenqian Yan, Baochang Zhang, Liujuan Cao, Qixiang Ye, Feiyue Huang, David Doermann
Abstract	Structured pruning of filters or neurons has received increased focus for compressing convolutional neural networks. Most existing methods rely on multi-stage optimizations in a layer-wise manner for iteratively pruning and retraining which may not be optimal and may be computation intensive. Besides, these methods are designed for pruning a specific structure, such as filter or block structures without jointly pruning heterogeneous structures. In this paper, we propose an effective structured pruning approach that jointly prunes filters as well as other structures in an end-to-end manner. To accomplish this, we first introduce a soft mask to scale the output of these structures by defining a new objective function with sparsity regularization to align the output of baseline and network with this mask. We then effectively solve the optimization problem by generative adversarial learning (GAL), which learns a sparse soft mask in a label-free and an end-to-end manner. By forcing more scaling factors in the soft mask to zero, the fast iterative shrinkage-thresholding algorithm (FISTA) can be leveraged to fast and reliably remove the corresponding structures. Extensive experiments demonstrate the effectiveness of GAL on different datasets, including MNIST, CIFAR-10 and ImageNet ILSVRC 2012. For example, on ImageNet ILSVRC 2012, the pruned ResNet-50 achieves 10.88% Top-5 error and results in a factor of 3.7x speedup. This significantly outperforms state-of-the-art methods.
Tasks
Published	2019-03-22
URL	http://arxiv.org/abs/1903.09291v1
PDF	http://arxiv.org/pdf/1903.09291v1.pdf
PWC	https://paperswithcode.com/paper/towards-optimal-structured-cnn-pruning-via
Repo
Framework

Private Deep Learning with Teacher Ensembles


Title	Private Deep Learning with Teacher Ensembles
Authors	Lichao Sun, Yingbo Zhou, Ji Wang, Jia Li, Richard Sochar, Philip S. Yu, Caiming Xiong
Abstract	Privacy-preserving deep learning is crucial for deploying deep neural network based solutions, especially when the model works on data that contains sensitive information. Most privacy-preserving methods lead to undesirable performance degradation. Ensemble learning is an effective way to improve model performance. In this work, we propose a new method for teacher ensembles that uses more informative network outputs under differential private stochastic gradient descent and provide provable privacy guarantees. Out method employs knowledge distillation and hint learning on intermediate representations to facilitate the training of student model. Additionally, we propose a simple weighted ensemble scheme that works more robustly across different teaching settings. Experimental results on three common image datasets benchmark (i.e., CIFAR10, MINST, and SVHN) demonstrate that our approach outperforms previous state-of-the-art methods on both performance and privacy-budget.
Tasks	Privacy Preserving Deep Learning
Published	2019-06-05
URL	https://arxiv.org/abs/1906.02303v2
PDF	https://arxiv.org/pdf/1906.02303v2.pdf
PWC	https://paperswithcode.com/paper/private-deep-learning-with-teacher-ensembles
Repo
Framework

Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric


Title	Understanding Adversarial Behavior of DNNs by Disentangling Non-Robust and Robust Components in Performance Metric
Authors	Yujun Shi, Benben Liao, Guangyong Chen, Yun Liu, Ming-Ming Cheng, Jiashi Feng
Abstract	The vulnerability to slight input perturbations is a worrying yet intriguing property of deep neural networks (DNNs). Despite many previous works studying the reason behind such adversarial behavior, the relationship between the generalization performance and adversarial behavior of DNNs is still little understood. In this work, we reveal such relation by introducing a metric characterizing the generalization performance of a DNN. The metric can be disentangled into an information-theoretic non-robust component, responsible for adversarial behavior, and a robust component. Then, we show by experiments that current DNNs rely heavily on optimizing the non-robust component in achieving decent performance. We also demonstrate that current state-of-the-art adversarial training algorithms indeed try to robustify the DNNs by preventing them from using the non-robust component to distinguish samples from different categories. Also, based on our findings, we take a step forward and point out the possible direction for achieving decent standard performance and adversarial robustness simultaneously. We believe that our theory could further inspire the community to make more interesting discoveries about the relationship between standard generalization and adversarial generalization of deep learning models.
Tasks
Published	2019-06-06
URL	https://arxiv.org/abs/1906.02494v1
PDF	https://arxiv.org/pdf/1906.02494v1.pdf
PWC	https://paperswithcode.com/paper/understanding-adversarial-behavior-of-dnns-by
Repo
Framework

State-aware Re-identification Feature for Multi-target Multi-camera Tracking


Title	State-aware Re-identification Feature for Multi-target Multi-camera Tracking
Authors	Peng Li, Jiabin Zhang, Zheng Zhu, Yanwei Li, Lu Jiang, Guan Huang
Abstract	Multi-target Multi-camera Tracking (MTMCT) aims to extract the trajectories from videos captured by a set of cameras. Recently, the tracking performance of MTMCT is significantly enhanced with the employment of re-identification (Re-ID) model. However, the appearance feature usually becomes unreliable due to the occlusion and orientation variance of the targets. Directly applying Re-ID model in MTMCT will encounter the problem of identity switches (IDS) and tracklet fragment caused by occlusion. To solve these problems, we propose a novel tracking framework in this paper. In this framework, the occlusion status and orientation information are utilized in Re-ID model with human pose information considered. In addition, the tracklet association using the proposed fused tracking feature is adopted to handle the fragment problem. The proposed tracker achieves 81.3% IDF1 on the multiple-camera hard sequence, which outperforms all other reference methods by a large margin.
Tasks
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01357v1
PDF	https://arxiv.org/pdf/1906.01357v1.pdf
PWC	https://paperswithcode.com/paper/state-aware-re-identification-feature-for
Repo
Framework

Extending planning knowledge using ontologies for goal opportunities


Title	Extending planning knowledge using ontologies for goal opportunities
Authors	Mohannad Babli, Eva Onaindia, Eliseo Marzal
Abstract	Approaches to goal-directed behaviour including online planning and opportunistic planning tackle a change in the environment by generating alternative goals to avoid failures or seize opportunities. However, current approaches only address unanticipated changes related to objects or object types already defined in the planning task that is being solved. This article describes a domain-independent approach that advances the state of the art by extending the knowledge of a planning task with relevant objects of new types. The approach draws upon the use of ontologies, semantic measures, and ontology alignment to accommodate newly acquired data that trigger the formulation of goal opportunities inducing a better-valued plan.
Tasks
Published	2019-04-07
URL	http://arxiv.org/abs/1904.03606v1
PDF	http://arxiv.org/pdf/1904.03606v1.pdf
PWC	https://paperswithcode.com/paper/extending-planning-knowledge-using-ontologies
Repo
Framework

A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation


Title	A Hierarchical Attention Based Seq2seq Model for Chinese Lyrics Generation
Authors	Haoshen Fan, Jie Wang, Bojin Zhuang, Shaojun Wang, Jing Xiao
Abstract	In this paper, we comprehensively study on context-aware generation of Chinese song lyrics. Conventional text generative models generate a sequence or sentence word by word, failing to consider the contextual relationship between sentences. Taking account into the characteristics of lyrics, a hierarchical attention based Seq2Seq (Sequence-to-Sequence) model is proposed for Chinese lyrics generation. With encoding of word-level and sentence-level contextual information, this model promotes the topic relevance and consistency of generation. A large Chinese lyrics corpus is also leveraged for model training. Eventually, results of automatic and human evaluations demonstrate that our model is able to compose complete Chinese lyrics with one united topic constraint.
Tasks
Published	2019-06-15
URL	https://arxiv.org/abs/1906.06481v1
PDF	https://arxiv.org/pdf/1906.06481v1.pdf
PWC	https://paperswithcode.com/paper/a-hierarchical-attention-based-seq2seq-model
Repo
Framework

Empirical study of extreme overfitting points of neural networks


Title	Empirical study of extreme overfitting points of neural networks
Authors	Daniil Merkulov, Ivan Oseledets
Abstract	In this paper we propose a method of obtaining points of extreme overfitting - parameters of modern neural networks, at which they demonstrate close to 100 % training accuracy, simultaneously with almost zero accuracy on the test sample. Despite the widespread opinion that the overwhelming majority of critical points of the loss function of a neural network have equally good generalizing ability, such points have a huge generalization error. The paper studies the properties of such points and their location on the surface of the loss function of modern neural networks.
Tasks
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06295v2
PDF	https://arxiv.org/pdf/1906.06295v2.pdf
PWC	https://paperswithcode.com/paper/empirical-study-of-extreme-overfitting-points
Repo
Framework

Intrusion detection systems using classical machine learning techniques versus integrated unsupervised feature learning and deep neural network


Title	Intrusion detection systems using classical machine learning techniques versus integrated unsupervised feature learning and deep neural network
Authors	Shisrut Rawat, Aishwarya Srinivasan, Vinayakumar R
Abstract	Security analysts and administrators face a lot of challenges to detect and prevent network intrusions in their organizations, and to prevent network breaches, detecting the breach on time is crucial. Challenges arise while detecting unforeseen attacks. This work includes a performance comparison of classical machine learning approaches that require vast feature engineering, versus integrated unsupervised feature learning and deep neural networks on the NSL-KDD dataset. Various trials of experiments were run to identify suitable hyper-parameters and network configurations of machine learning models. The DNN using 15 features extracted using Principal Component analysis was the most effective modeling method. The further analysis using the Software Defined Networking features also presented a good accuracy using Deep Neural network.
Tasks	Feature Engineering, Intrusion Detection
Published	2019-10-01
URL	https://arxiv.org/abs/1910.01114v1
PDF	https://arxiv.org/pdf/1910.01114v1.pdf
PWC	https://paperswithcode.com/paper/intrusion-detection-systems-using-classical
Repo
Framework

Global Reasoning over Database Structures for Text-to-SQL Parsing


Title	Global Reasoning over Database Structures for Text-to-SQL Parsing
Authors	Ben Bogin, Matt Gardner, Jonathan Berant
Abstract	State-of-the-art semantic parsers rely on auto-regressive decoding, emitting one symbol at a time. When tested against complex databases that are unobserved at training time (zero-shot), the parser often struggles to select the correct set of database constants in the new database, due to the local nature of decoding. In this work, we propose a semantic parser that globally reasons about the structure of the output query to make a more contextually-informed selection of database constants. We use message-passing through a graph neural network to softly select a subset of database constants for the output query, conditioned on the question. Moreover, we train a model to rank queries based on the global alignment of database constants to question words. We apply our techniques to the current state-of-the-art model for Spider, a zero-shot semantic parsing dataset with complex databases, increasing accuracy from 39.4% to 47.4%.
Tasks	Semantic Parsing, Text-To-Sql
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11214v1
PDF	https://arxiv.org/pdf/1908.11214v1.pdf
PWC	https://paperswithcode.com/paper/global-reasoning-over-database-structures-for
Repo
Framework

Detecting malicious logins as graph anomalies


Title	Detecting malicious logins as graph anomalies
Authors	Brian A. Powell
Abstract	Authenticated lateral movement via compromised accounts is a common adversarial maneuver that is challenging to discover with signature- or rules-based intrusion detection systems. In this work a behavior-based approach to detecting malicious logins to novel systems indicative of lateral movement is presented, in which a user’s historical login activity is used to build a model of putative “normal” behavior. This historical login activity is represented as a collection of daily login graphs, which encode authentications among accessed systems. Each system, or graph vertex, is described by a set of graph centrality measures that characterize it and the local topology of its login graph. The unsupervised technique of non-negative matrix factorization is then applied to this set of features to assign each vertex to a role that summarizes how the system participates in logins. The reconstruction error quantifying how well each vertex fits into its role is then computed, and the statistics of this error can be used to identify outlier vertices that correspond to systems involved in unusual logins. We test this technique with a small cohort of privileged accounts using real login data from an operational enterprise network. The ability of the method to identify malicious logins among normal activity is tested with simulated graphs of login activity representative of adversarial lateral movement. We find that the method is generally successful at detecting a broad range of lateral movement for each user, with false positive rates significantly lower than those resulting from alerts based solely on login novelty.
Tasks	Intrusion Detection
Published	2019-09-19
URL	https://arxiv.org/abs/1909.09047v2
PDF	https://arxiv.org/pdf/1909.09047v2.pdf
PWC	https://paperswithcode.com/paper/detecting-malicious-logins-as-graph-anomalies
Repo
Framework

Running Time Analysis of the (1+1)-EA for Robust Linear Optimization


Title	Running Time Analysis of the (1+1)-EA for Robust Linear Optimization
Authors	Chao Bian, Chao Qian, Ke Tang
Abstract	Evolutionary algorithms (EAs) have found many successful real-world applications, where the optimization problems are often subject to a wide range of uncertainties. To understand the practical behaviors of EAs theoretically, there are a series of efforts devoted to analyzing the running time of EAs for optimization under uncertainties. Existing studies mainly focus on noisy and dynamic optimization, while another common type of uncertain optimization, i.e., robust optimization, has been rarely touched. In this paper, we analyze the expected running time of the (1+1)-EA solving robust linear optimization problems (i.e., linear problems under robust scenarios) with a cardinality constraint $k$. Two common robust scenarios, i.e., deletion-robust and worst-case, are considered. Particularly, we derive tight ranges of the robust parameter $d$ or budget $k$ allowing the (1+1)-EA to find an optimal solution in polynomial running time, which disclose the potential of EAs for robust optimization.
Tasks
Published	2019-06-17
URL	https://arxiv.org/abs/1906.06873v1
PDF	https://arxiv.org/pdf/1906.06873v1.pdf
PWC	https://paperswithcode.com/paper/running-time-analysis-of-the-11-ea-for-robust
Repo
Framework