January 27, 2020

3246 words 16 mins read

Paper Group ANR 1313

Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle. MobileGAN: Skin Lesion Segmentation Using a Lightweight Generative Adversarial Network. There are No Bit Parts for Sign Bits in Black-Box Attacks. Gaussian DAGs on network data. Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders. …

Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle


Title	Reward Advancement: Transforming Policy under Maximum Causal Entropy Principle
Authors	Guojun Wu, Yanhua Li, Zhenming Liu, Jie Bao, Yu Zheng, Jieping Ye, Jun Luo
Abstract	Many real-world human behaviors can be characterized as a sequential decision making processes, such as urban travelers choices of transport modes and routes (Wu et al. 2017). Differing from choices controlled by machines, which in general follows perfect rationality to adopt the policy with the highest reward, studies have revealed that human agents make sub-optimal decisions under bounded rationality (Tao, Rohde, and Corcoran 2014). Such behaviors can be modeled using maximum causal entropy (MCE) principle (Ziebart 2010). In this paper, we define and investigate a general reward trans-formation problem (namely, reward advancement): Recovering the range of additional reward functions that transform the agent’s policy from original policy to a predefined target policy under MCE principle. We show that given an MDP and a target policy, there are infinite many additional reward functions that can achieve the desired policy transformation. Moreover, we propose an algorithm to further extract the additional rewards with minimum “cost” to implement the policy transformation.
Tasks	Decision Making
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05390v1
PDF	https://arxiv.org/pdf/1907.05390v1.pdf
PWC	https://paperswithcode.com/paper/reward-advancement-transforming-policy-under
Repo
Framework

MobileGAN: Skin Lesion Segmentation Using a Lightweight Generative Adversarial Network


Title	MobileGAN: Skin Lesion Segmentation Using a Lightweight Generative Adversarial Network
Authors	Md. Mostafa Kamal Sarker, Hatem A. Rashwan, Mohamed Abdel-Nasser, Vivek Kumar Singh, Syeda Furruka Banu, Farhan Akram, Forhad U H Chowdhury, Kabir Ahmed Choudhury, Sylvie Chambon, Petia Radeva, Domenec Puig
Abstract	Skin lesion segmentation in dermoscopic images is a challenge due to their blurry and irregular boundaries. Most of the segmentation approaches based on deep learning are time and memory consuming due to the hundreds of millions of parameters. Consequently, it is difficult to apply them to real dermatoscope devices with limited GPU and memory resources. In this paper, we propose a lightweight and efficient Generative Adversarial Networks (GAN) model, called MobileGAN for skin lesion segmentation. More precisely, the MobileGAN combines 1D non-bottleneck factorization networks with position and channel attention modules in a GAN model. The proposed model is evaluated on the test dataset of the ISBI 2017 challenges and the validation dataset of ISIC 2018 challenges. Although the proposed network has only 2.35 millions of parameters, it is still comparable with the state-of-the-art. The experimental results show that our MobileGAN obtains comparable performance with an accuracy of 97.61%.
Tasks	Lesion Segmentation
Published	2019-07-01
URL	https://arxiv.org/abs/1907.00856v1
PDF	https://arxiv.org/pdf/1907.00856v1.pdf
PWC	https://paperswithcode.com/paper/mobilegan-skin-lesion-segmentation-using-a
Repo
Framework

There are No Bit Parts for Sign Bits in Black-Box Attacks


Title	There are No Bit Parts for Sign Bits in Black-Box Attacks
Authors	Abdullah Al-Dujaili, Una-May O’Reilly
Abstract	We present a black-box adversarial attack algorithm which sets new state-of-the-art model evasion rates for query efficiency in the $\ell_\infty$ and $\ell_2$ metrics, where only loss-oracle access to the model is available. On two public black-box attack challenges, the algorithm achieves the highest evasion rate, surpassing all of the submitted attacks. Similar performance is observed on a model that is secure against substitute-model attacks. For standard models trained on the MNIST, CIFAR10, and IMAGENET datasets, averaged over the datasets and metrics, the algorithm is 3.8x less failure-prone, and spends in total 2.5x fewer queries than the current state-of-the-art attacks combined given a budget of 10, 000 queries per attack attempt. Notably, it requires no hyperparameter tuning or any data/time-dependent prior. The algorithm exploits a new approach, namely sign-based rather than magnitude-based gradient estimation. This shifts the estimation from continuous to binary black-box optimization. With three properties of the directional derivative, we examine three approaches to adversarial attacks. This yields a superior algorithm breaking a standard MNIST model using just 12 queries on average!
Tasks	Adversarial Attack
Published	2019-02-19
URL	http://arxiv.org/abs/1902.06894v4
PDF	http://arxiv.org/pdf/1902.06894v4.pdf
PWC	https://paperswithcode.com/paper/there-are-no-bit-parts-for-sign-bits-in-black
Repo
Framework

Gaussian DAGs on network data


Title	Gaussian DAGs on network data
Authors	Hangjian Li, Qing Zhou
Abstract	The traditional directed acyclic graph (DAG) model assumes data are generated independently from the underlying joint distribution defined by the DAG. In many applications, however, individuals are linked via a network and thus the independence assumption does not hold. We propose a novel Gaussian DAG model for network data, where the dependence among individual data points (row covariance) is modeled by an undirected graph. Under this model, we develop a maximum penalized likelihood method to estimate the DAG structure and the row correlation matrix. The algorithm iterates between a decoupled lasso regression step and a graphical lasso step. We show with extensive simulated and real network data, that our algorithm improves the accuracy of DAG structure learning by leveraging the information from the estimated row correlations. Moreover, we demonstrate that the performance of existing DAG learning methods can be substantially improved via de-correlation of network data with the estimated row correlation matrix from our algorithm.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10848v1
PDF	https://arxiv.org/pdf/1905.10848v1.pdf
PWC	https://paperswithcode.com/paper/gaussian-dags-on-network-data
Repo
Framework

Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders


Title	Pre-train and Plug-in: Flexible Conditional Text Generation with Variational Auto-Encoders
Authors	Yu Duan, Jiaxin Pei, Canwen Xu, Chenliang Li
Abstract	Current neural Natural Language Generation (NLG) models cannot handle emerging conditions due to their joint end-to-end learning fashion. When the need for generating text under a new condition emerges, these techniques require not only sufficiently supplementary labeled data but also a full re-training of the existing model. In this paper, we present a new framework named Hierarchical Neural Auto-Encoder (HAE) toward flexible conditional text generation. HAE decouples the text generation module from the condition representation module to allow “one-to-many” conditional generation. When a fresh condition emerges, only a lightweight network needs to be trained and works as a plug-in for HAE, which is efficient and desirable for real-world applications. Extensive experiments demonstrate the superiority of HAE against the existing alternatives with much less training time and fewer model parameters.
Tasks	Text Generation
Published	2019-11-10
URL	https://arxiv.org/abs/1911.03882v1
PDF	https://arxiv.org/pdf/1911.03882v1.pdf
PWC	https://paperswithcode.com/paper/pre-train-and-plug-in-flexible-conditional
Repo
Framework

Fisher Discriminative Least Square Regression with Self-Adaptive Weighting for Face Recognition


Title	Fisher Discriminative Least Square Regression with Self-Adaptive Weighting for Face Recognition
Authors	Zhe Chen, Xiao-Jun Wu, Josef Kittler
Abstract	As a supervised classification method, least square regression (LSR) has shown promising performance in multiclass face recognition tasks. However, the latest LSR based classification methods mainly focus on learning a relaxed regression target to replace traditional zero-one label matrix while ignoring the discriminability of transformed features. Based on the assumption that the transformed features of samples from the same class have similar structure while those of samples from different classes are uncorrelated, in this paper we propose a novel discriminative LSR method based on the Fisher discrimination criterion (FDLSR), where the projected features have small within-class scatter and large inter-class scatter simultaneously. Moreover, different from other methods, we explore relax regression from the view of transformed features rather than the regression targets. Specifically, we impose a dynamic non-negative weight matrix on the transformed features to enlarge the margin between the true and the false classes by self-adaptively assigning appropriate weights to different features. Above two factors can encourage the learned transformation for regression to be more discriminative and thus achieving better classification performance. Extensive experiments on various databases demonstrate that the proposed FDLSR method achieves superior performance to other state-of-the-art LSR based classification methods.
Tasks	Face Recognition
Published	2019-03-19
URL	https://arxiv.org/abs/1903.07833v2
PDF	https://arxiv.org/pdf/1903.07833v2.pdf
PWC	https://paperswithcode.com/paper/fisher-discriminative-least-square-regression
Repo
Framework

Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies


Title	Towards Non-saturating Recurrent Units for Modelling Long-term Dependencies
Authors	Sarath Chandar, Chinnadhurai Sankar, Eugene Vorontsov, Samira Ebrahimi Kahou, Yoshua Bengio
Abstract	Modelling long-term dependencies is a challenge for recurrent neural networks. This is primarily due to the fact that gradients vanish during training, as the sequence length increases. Gradients can be attenuated by transition operators and are attenuated or dropped by activation functions. Canonical architectures like LSTM alleviate this issue by skipping information through a memory mechanism. We propose a new recurrent architecture (Non-saturating Recurrent Unit; NRU) that relies on a memory mechanism but forgoes both saturating activation functions and saturating gates, in order to further alleviate vanishing gradients. In a series of synthetic and real world tasks, we demonstrate that the proposed model is the only model that performs among the top 2 models across all tasks with and without long-term dependencies, when compared against a range of other architectures.
Tasks
Published	2019-01-22
URL	http://arxiv.org/abs/1902.06704v1
PDF	http://arxiv.org/pdf/1902.06704v1.pdf
PWC	https://paperswithcode.com/paper/towards-non-saturating-recurrent-units-for
Repo
Framework

Large-Scale Landslides Detection from Satellite Images with Incomplete Labels


Title	Large-Scale Landslides Detection from Satellite Images with Incomplete Labels
Authors	Masanari Kimura
Abstract	Earthquakes and tropical cyclones cause the suffering of millions of people around the world every year. The resulting landslides exacerbate the effects of these disasters. Landslide detection is, therefore, a critical task for the protection of human life and livelihood in mountainous areas. To tackle this problem, we propose a combination of satellite technology and Deep Neural Networks (DNNs). We evaluate the performance of multiple DNN-based methods for landslide detection on actual satellite images of landslide damage. Our analysis demonstrates the potential for a meaningful social impact in terms of disasters and rescue.
Tasks
Published	2019-10-16
URL	https://arxiv.org/abs/1910.07129v1
PDF	https://arxiv.org/pdf/1910.07129v1.pdf
PWC	https://paperswithcode.com/paper/large-scale-landslides-detection-from
Repo
Framework

Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks


Title	Infusing Knowledge into the Textual Entailment Task Using Graph Convolutional Networks
Authors	Pavan Kapanipathi, Veronika Thost, Siva Sankalp Patel, Spencer Whitehead, Ibrahim Abdelaziz, Avinash Balakrishnan, Maria Chang, Kshitij Fadnis, Chulaka Gunasekara, Bassem Makni, Nicholas Mattei, Kartik Talamadupula, Achille Fokoue
Abstract	Textual entailment is a fundamental task in natural language processing. Most approaches for solving the problem use only the textual content present in training data. A few approaches have shown that information from external knowledge sources like knowledge graphs (KGs) can add value, in addition to the textual content, by providing background knowledge that may be critical for a task. However, the proposed models do not fully exploit the information in the usually large and noisy KGs, and it is not clear how it can be effectively encoded to be useful for entailment. We present an approach that complements text-based entailment models with information from KGs by (1) using Personalized PageR- ank to generate contextual subgraphs with reduced noise and (2) encoding these subgraphs using graph convolutional networks to capture KG structure. Our technique extends the capability of text models exploiting structural and semantic information found in KGs. We evaluate our approach on multiple textual entailment datasets and show that the use of external knowledge helps improve prediction accuracy. This is particularly evident in the challenging BreakingNLI dataset, where we see an absolute improvement of 5-20% over multiple text-based entailment models.
Tasks	Knowledge Graphs, Natural Language Inference
Published	2019-11-05
URL	https://arxiv.org/abs/1911.02060v2
PDF	https://arxiv.org/pdf/1911.02060v2.pdf
PWC	https://paperswithcode.com/paper/infusing-knowledge-into-the-textual
Repo
Framework

Estimating Granger Causality with Unobserved Confounders via Deep Latent-Variable Recurrent Neural Network


Title	Estimating Granger Causality with Unobserved Confounders via Deep Latent-Variable Recurrent Neural Network
Authors	Yuan Meng
Abstract	Granger causality analysis, as one of the most popular time series causality methods, has been widely used in the economics, neuroscience. However, unobserved confounders is a fundamental problem in the observational studies, which is still not solved for the non-linear Granger causality. The application works often deal with this problem in virtue of the proxy variables, who can be treated as a measure of the confounder with noise. But the proxy variables has been proved to be unreliable, because of the bias it may induce. In this paper, we try to “recover” the unobserved confounders for the Granger causality. We use a generative model with latent variable to build the relationship between the unobserved confounders and the observed variables(tested variable and the proxy variables). The posterior distribution of the latent variable is adopted to represent the confounders distribution, which can be sampled to get the estimated confounders. We adopt the variational autoencoder to estimate the intractable posterior distribution. The recurrent neural network is applied to build the temporal relationship in the data. We evaluate our method in the synthetic and semi-synthetic dataset. The result shows our estimated confounders has a better performance than the proxy variables in the non-linear Granger causality with multiple proxies in the semi-synthetic dataset. But the performances of the synthetic dataset and the different noise level of proxy seem terrible. Any advice can really help.
Tasks	Time Series
Published	2019-09-09
URL	https://arxiv.org/abs/1909.03704v1
PDF	https://arxiv.org/pdf/1909.03704v1.pdf
PWC	https://paperswithcode.com/paper/estimating-granger-causality-with-unobserved
Repo
Framework

Towards Neural Decompilation


Title	Towards Neural Decompilation
Authors	Omer Katz, Yuval Olshaker, Yoav Goldberg, Eran Yahav
Abstract	We address the problem of automatic decompilation, converting a program in low-level representation back to a higher-level human-readable programming language. The problem of decompilation is extremely important for security researchers. Finding vulnerabilities and understanding how malware operates is much easier when done over source code. The importance of decompilation has motivated the construction of hand-crafted rule-based decompilers. Such decompilers have been designed by experts to detect specific control-flow structures and idioms in low-level code and lift them to source level. The cost of supporting additional languages or new language features in these models is very high. We present a novel approach to decompilation based on neural machine translation. The main idea is to automatically learn a decompiler from a given compiler. Given a compiler from a source language S to a target language T , our approach automatically trains a decompiler that can translate (decompile) T back to S . We used our framework to decompile both LLVM IR and x86 assembly to C code with high success rates. Using our LLVM and x86 instantiations, we were able to successfully decompile over 97% and 88% of our benchmarks respectively.
Tasks	Machine Translation
Published	2019-05-20
URL	https://arxiv.org/abs/1905.08325v1
PDF	https://arxiv.org/pdf/1905.08325v1.pdf
PWC	https://paperswithcode.com/paper/towards-neural-decompilation
Repo
Framework

Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation


Title	Learning Spatial Pyramid Attentive Pooling in Image Synthesis and Image-to-Image Translation
Authors	Wei Sun, Tianfu Wu
Abstract	Image synthesis and image-to-image translation are two important generative learning tasks. Remarkable progress has been made by learning Generative Adversarial Networks (GANs)~\cite{goodfellow2014generative} and cycle-consistent GANs (CycleGANs)~\cite{zhu2017unpaired} respectively. This paper presents a method of learning Spatial Pyramid Attentive Pooling (SPAP) which is a novel architectural unit and can be easily integrated into both generators and discriminators in GANs and CycleGANs. The proposed SPAP integrates Atrous spatial pyramid~\cite{chen2018deeplab}, a proposed cascade attention mechanism and residual connections~\cite{he2016deep}. It leverages the advantages of the three components to facilitate effective end-to-end generative learning: (i) the capability of fusing multi-scale information by ASPP; (ii) the capability of capturing relative importance between both spatial locations (especially multi-scale context) or feature channels by attention; (iii) the capability of preserving information and enhancing optimization feasibility by residual connections. Coarse-to-fine and fine-to-coarse SPAP are studied and intriguing attention maps are observed in both tasks. In experiments, the proposed SPAP is tested in GANs on the Celeba-HQ-128 dataset~\cite{karras2017progressive}, and tested in CycleGANs on the Image-to-Image translation datasets including the Cityscape dataset~\cite{cordts2016cityscapes}, Facade and Aerial Maps dataset~\cite{zhu2017unpaired}, both obtaining better performance.
Tasks	Image Generation, Image-to-Image Translation
Published	2019-01-18
URL	http://arxiv.org/abs/1901.06322v1
PDF	http://arxiv.org/pdf/1901.06322v1.pdf
PWC	https://paperswithcode.com/paper/learning-spatial-pyramid-attentive-pooling-in
Repo
Framework

Long Short-Term Memory Neural Networks for False Information Attack Detection in Software-Defined In-Vehicle Network


Title	Long Short-Term Memory Neural Networks for False Information Attack Detection in Software-Defined In-Vehicle Network
Authors	Zadid Khan, Mashrur Chowdhury, Mhafuzul Islam, Chin-Ya Huang, Mizanur Rahman
Abstract	A modern vehicle contains many electronic control units (ECUs), which communicate with each other through the in-vehicle network to ensure vehicle safety and performance. Emerging Connected and Automated Vehicles (CAVs) will have more ECUs and coupling between them due to the vast array of additional sensors, advanced driving features and Vehicle-to-Everything (V2X) connectivity. Due to the connectivity, CAVs will be more vulnerable to remote attackers. In this study, we developed a software-defined in-vehicle Ethernet networking system that provides security against false information attacks. We then created an attack model and attack datasets for false information attacks on brake-related ECUs. After analyzing the attack dataset, we found that the features of the dataset are time-series that have sequential variation patterns. Therefore, we subsequently developed a long short term memory (LSTM) neural network based false information attack/anomaly detection model for the real-time detection of anomalies within the in-vehicle network. This attack detection model can detect false information with an accuracy, precision and recall of 95%, 95% and 87%, respectively, while satisfying the real-time communication and computational requirements.
Tasks	Anomaly Detection, Time Series, Time Series Classification
Published	2019-06-24
URL	https://arxiv.org/abs/1906.10203v2
PDF	https://arxiv.org/pdf/1906.10203v2.pdf
PWC	https://paperswithcode.com/paper/in-vehicle-false-information-attack-detection
Repo
Framework

A New Deterministic Technique for Symbolic Regression


Title	A New Deterministic Technique for Symbolic Regression
Authors	Daniel Rivero, Enrique Fernandez-Blanco
Abstract	This paper describes a new method for Symbolic Regression that allows to find mathematical expressions from a dataset. This method has a strong mathematical basis. As opposed to other methods such as Genetic Programming, this method is deterministic, and does not involve the creation of a population of initial solutions. Instead of it, a simple expression is being grown until it fits the data. The experiments performed show that the results are as good as other Machine Learning methods, in a very low computational time. Another advantage of this technique is that the complexity of the expressions can be limited, so the system can return mathematical expressions that can be easily analysed by the user, in opposition to other techniques like GSGP.
Tasks
Published	2019-08-16
URL	https://arxiv.org/abs/1908.06754v4
PDF	https://arxiv.org/pdf/1908.06754v4.pdf
PWC	https://paperswithcode.com/paper/a-new-deterministic-technique-for-symbolic
Repo
Framework

Video Rain/Snow Removal by Transformed Online Multiscale Convolutional Sparse Coding


Title	Video Rain/Snow Removal by Transformed Online Multiscale Convolutional Sparse Coding
Authors	Minghan Li, Xiangyong Cao, Qian Zhao, Lei Zhang, Chenqiang Gao, Deyu Meng
Abstract	Video rain/snow removal from surveillance videos is an important task in the computer vision community since rain/snow existed in videos can severely degenerate the performance of many surveillance system. Various methods have been investigated extensively, but most only consider consistent rain/snow under stable background scenes. Rain/snow captured from practical surveillance camera, however, is always highly dynamic in time with the background scene transformed occasionally. To this issue, this paper proposes a novel rain/snow removal approach, which fully considers dynamic statistics of both rain/snow and background scenes taken from a video sequence. Specifically, the rain/snow is encoded as an online multi-scale convolutional sparse coding (OMS-CSC) model, which not only finely delivers the sparse scattering and multi-scale shapes of real rain/snow, but also well encodes their temporally dynamic configurations by real-time ameliorated parameters in the model. Furthermore, a transformation operator imposed on the background scenes is further embedded into the proposed model, which finely conveys the dynamic background transformations, such as rotations, scalings and distortions, inevitably existed in a real video sequence. The approach so constructed can naturally better adapt to the dynamic rain/snow as well as background changes, and also suitable to deal with the streaming video attributed its online learning mode. The proposed model is formulated in a concise maximum a posterior (MAP) framework and is readily solved by the ADMM algorithm. Compared with the state-of-the-art online and offline video rain/snow removal methods, the proposed method achieves better performance on synthetic and real videos datasets both visually and quantitatively. Specifically, our method can be implemented in relatively high efficiency, showing its potential to real-time video rain/snow removal.
Tasks
Published	2019-09-13
URL	https://arxiv.org/abs/1909.06148v1
PDF	https://arxiv.org/pdf/1909.06148v1.pdf
PWC	https://paperswithcode.com/paper/video-rainsnow-removal-by-transformed-online
Repo
Framework