January 26, 2020

2987 words 15 mins read

Paper Group ANR 1445

Effects of Foraging in Personalized Content-based Image Recommendation. Discovering Differential Features: Adversarial Learning for Information Credibility Evaluation. NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining. Manipulation Motion Taxonomy and Coding for Robots. Faster saddle-point optimization for solving large-scale …

Effects of Foraging in Personalized Content-based Image Recommendation


Title	Effects of Foraging in Personalized Content-based Image Recommendation
Authors	Amit Kumar Jaiswal, Haiming Liu, Ingo Frommholz
Abstract	A major challenge of recommender systems is to help users locating interesting items. Personalized recommender systems have become very popular as they attempt to predetermine the needs of users and provide them with recommendations to personalize their navigation. However, few studies have addressed the question of what drives the users’ attention to specific content within the collection and what influences the selection of interesting items. To this end, we employ the lens of Information Foraging Theory (IFT) to image recommendation to demonstrate how the user could utilize visual bookmarks to locate interesting images. We investigate a personalized content-based image recommendation system to understand what affects user attention by reinforcing visual attention cues based on IFT. We further find that visual bookmarks (cues) lead to a stronger scent of the recommended image collection. Our evaluation is based on the Pinterest image collection.
Tasks	Recommendation Systems
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00483v2
PDF	https://arxiv.org/pdf/1907.00483v2.pdf
PWC	https://paperswithcode.com/paper/effects-of-foraging-in-personalized-content
Repo
Framework

Discovering Differential Features: Adversarial Learning for Information Credibility Evaluation


Title	Discovering Differential Features: Adversarial Learning for Information Credibility Evaluation
Authors	Lianwei Wu, Yuan Rao, Ambreen Nazir, Haolin Jin
Abstract	A series of deep learning approaches extract a large number of credibility features to detect fake news on the Internet. However, these extracted features still suffer from many irrelevant and noisy features that restrict severely the performance of the approaches. In this paper, we propose a novel model based on Adversarial Networks and inspirited by the Shared-Private model (ANSP), which aims at reducing common, irrelevant features from the extracted features for information credibility evaluation. Specifically, ANSP involves two tasks: one is to prevent the binary classification of true and false information for capturing common features relying on adversarial networks guided by reinforcement learning. Another extracts credibility features (henceforth, private features) from multiple types of credibility information and compares with the common features through two strategies, i.e., orthogonality constraints and KL-divergence for making the private features more differential. Experiments first on two six-label LIAR and Weibo datasets demonstrate that ANSP achieves the state-of-the-art performance, boosting the accuracy by 2.1%, 3.1%, respectively and then on four-label Twitter16 validate the robustness of the model with 1.8% performance improvements.
Tasks
Published	2019-09-16
URL	https://arxiv.org/abs/1909.07523v1
PDF	https://arxiv.org/pdf/1909.07523v1.pdf
PWC	https://paperswithcode.com/paper/discovering-differential-features-adversarial
Repo
Framework

NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining


Title	NASNet: A Neuron Attention Stage-by-Stage Net for Single Image Deraining
Authors	Xu Qin, Zhilin Wang
Abstract	Images captured under complicated rain conditions often suffer from noticeable degradation of visibility. The rain models generally introduce diversity visibility degradation, which includes rain streak, rain drop as well as rain mist. Numerous existing single image deraining methods focus on the only one type rain model, which does not have strong generalization ability. In this paper, we propose a novel end-to-end Neuron Attention Stage-by-Stage Net (NASNet), which can solve all types of rain model tasks efficiently. For one thing, we pay more attention on the Neuron relationship and propose a lightweight Neuron Attention (NA) architectural mechanism. It can adaptively recalibrate neuron-wise feature responses by modelling interdependencies and mutual influence between neurons. Our NA architecture consists of Depthwise Conv and Pointwise Conv, which has slight computation cost and higher performance than SE block by our contrasted experiments. For another, we propose a stage-by-stage unified pattern network architecture, the stage-by-stage strategy guides the later stage by incorporating the useful information in previous stage. We concatenate and fuse stage-level information dynamically by NA module. Extensive experiments demonstrate that our proposed NASNet significantly outperforms the state-of-theart methods by a large margin in terms of both quantitative and qualitative measures on all six public large-scale datasets for three rain model tasks.
Tasks	Rain Removal, Single Image Deraining
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03151v1
PDF	https://arxiv.org/pdf/1912.03151v1.pdf
PWC	https://paperswithcode.com/paper/nasnet-a-neuron-attention-stage-by-stage-net
Repo
Framework

Manipulation Motion Taxonomy and Coding for Robots


Title	Manipulation Motion Taxonomy and Coding for Robots
Authors	David Paulius, Yongqiang Huang, Jason Meloncon, Yu Sun
Abstract	This paper introduces a taxonomy of manipulations as seen especially in cooking for 1) grouping manipulations from the robotics point of view, 2) consolidating aliases and removing ambiguity for motion types, and 3) provide a path to transferring learned manipulations to new unlearned manipulations. Using instructional videos as a reference, we selected a list of common manipulation motions seen in cooking activities grouped into similar motions based on several trajectory and contact attributes. Manipulation codes are then developed based on the taxonomy attributes to represent the manipulation motions. The manipulation taxonomy is then used for comparing motion data in the Daily Interactive Manipulation (DIM) data set to reveal their motion similarities.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00532v1
PDF	https://arxiv.org/pdf/1910.00532v1.pdf
PWC	https://paperswithcode.com/paper/manipulation-motion-taxonomy-and-coding-for
Repo
Framework

Faster saddle-point optimization for solving large-scale Markov decision processes


Title	Faster saddle-point optimization for solving large-scale Markov decision processes
Authors	Joan Bas-Serrano, Gergely Neu
Abstract	We consider the problem of computing optimal policies in average-reward Markov decision processes. This classical problem can be formulated as a linear program directly amenable to saddle-point optimization methods, albeit with a number of variables that is linear in the number of states. To address this issue, recent work has considered a linearly relaxed version of the resulting saddle-point problem. Our work aims at achieving a better understanding of this relaxed optimization problem by characterizing the conditions necessary for convergence to the optimal policy, and designing an optimization algorithm enjoying fast convergence rates that are independent of the size of the state space. Notably, our characterization points out some potential issues with previous work.
Tasks
Published	2019-09-22
URL	https://arxiv.org/abs/1909.10904v2
PDF	https://arxiv.org/pdf/1909.10904v2.pdf
PWC	https://paperswithcode.com/paper/faster-saddle-point-optimization-for-solving
Repo
Framework

A Coarse-to-Fine Multi-stream Hybrid Deraining Network for Single Image Deraining


Title	A Coarse-to-Fine Multi-stream Hybrid Deraining Network for Single Image Deraining
Authors	Yanyan Wei, Zhao Zhang, Haijun Zhang, Richang Hong, Meng Wang
Abstract	Single image deraining task is still a very challenging task due to its ill-posed nature in reality. Recently, researchers have tried to fix this issue by training the CNN-based end-to-end models, but they still cannot extract the negative rain streaks from rainy images precisely, which usually leads to an over de-rained or under de-rained result. To handle this issue, this paper proposes a new coarse-to-fine single image deraining framework termed Multi-stream Hybrid Deraining Network (shortly, MH-DerainNet). To obtain the negative rain streaks during training process more accurately, we present a new module named dual path residual dense block, i.e., Residual path and Dense path. The Residual path is used to reuse com-mon features from the previous layers while the Dense path can explore new features. In addition, to concatenate different scaled features, we also apply the idea of multi-stream with shortcuts between cascaded dual path residual dense block based streams. To obtain more distinct derained images, we combine the SSIM loss and perceptual loss to preserve the per-pixel similarity as well as preserving the global structures so that the deraining result is more accurate. Extensive experi-ments on both synthetic and real rainy images demonstrate that our MH-DerainNet can deliver significant improvements over several recent state-of-the-art methods.
Tasks	Rain Removal, Single Image Deraining
Published	2019-08-28
URL	https://arxiv.org/abs/1908.10521v1
PDF	https://arxiv.org/pdf/1908.10521v1.pdf
PWC	https://paperswithcode.com/paper/a-coarse-to-fine-multi-stream-hybrid
Repo
Framework

FALCON: Fast and Lightweight Convolution for Compressing and Accelerating CNN


Title	FALCON: Fast and Lightweight Convolution for Compressing and Accelerating CNN
Authors	Chun Quan, Jun-Gi Jang, Hyun Dong Lee, U Kang
Abstract	How can we efficiently compress Convolutional Neural Networks (CNN) while retaining their accuracy on classification tasks? A promising direction is based on depthwise separable convolution which replaces a standard convolution with a depthwise convolution and a pointwise convolution. However, previous works based on depthwise separable convolution are limited since 1) they are mostly heuristic approaches without a precise understanding of their relations to standard convolution, and 2) their accuracies do not match that of the standard convolution. In this paper, we propose FALCON, an accurate and lightweight method for compressing CNN. FALCON is derived by interpreting existing convolution methods based on depthwise separable convolution using EHP, our proposed mathematical formulation to approximate the standard convolution kernel. Such interpretation leads to developing a generalized version rank-k FALCON which further improves the accuracy while sacrificing a bit of compression and computation reduction rates. In addition, we propose FALCON-branch by fitting FALCON into the previous state-of-the-art convolution unit ShuffleUnitV2 which gives even better accuracy. Experiments show that FALCON and FALCON-branch outperform 1) existing methods based on depthwise separable convolution and 2) standard CNN models by up to 8x compression and 8x computation reduction while ensuring similar accuracy. We also demonstrate that rank-k FALCON provides even better accuracy than standard convolution in many cases, while using a smaller number of parameters and floating-point operations.
Tasks
Published	2019-09-25
URL	https://arxiv.org/abs/1909.11321v1
PDF	https://arxiv.org/pdf/1909.11321v1.pdf
PWC	https://paperswithcode.com/paper/falcon-fast-and-lightweight-convolution-for
Repo
Framework

Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning


Title	Multi-Domain Adaptation in Brain MRI through Paired Consistency and Adversarial Learning
Authors	Mauricio Orbes-Arteaga, Thomas Varsavsky, Carole H. Sudre, Zach Eaton-Rosen, Lewis J. Haddow, Lauge Sørensen, Mads Nielsen, Akshay Pai, Sébastien Ourselin, Marc Modat, Parashkev Nachev, M. Jorge Cardoso
Abstract	Supervised learning algorithms trained on medical images will often fail to generalize across changes in acquisition parameters. Recent work in domain adaptation addresses this challenge and successfully leverages labeled data in a source domain to perform well on an unlabeled target domain. Inspired by recent work in semi-supervised learning we introduce a novel method to adapt from one source domain to $n$ target domains (as long as there is paired data covering all domains). Our multi-domain adaptation method utilises a consistency loss combined with adversarial learning. We provide results on white matter lesion hyperintensity segmentation from brain MRIs using the MICCAI 2017 challenge data as the source domain and two target domains. The proposed method significantly outperforms other domain adaptation baselines.
Tasks	Domain Adaptation
Published	2019-08-16
URL	https://arxiv.org/abs/1908.05959v2
PDF	https://arxiv.org/pdf/1908.05959v2.pdf
PWC	https://paperswithcode.com/paper/multi-domain-adaptation-in-brain-mri-through
Repo
Framework

Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks


Title	Fingerprint Presentation Attack Detection Based on Local Features Encoding for Unknown Attacks
Authors	Lázaro J. González-Soler, Marta Gomez-Barrero, Leonardo Chang, Airel Pérez-Suárez, Christoph Busch
Abstract	Fingerprint-based biometric systems have experienced a large development in the last years. Despite their many advantages, they are still vulnerable to presentation attacks (PAs). Therefore, the task of determining whether a sample stems from a live subject (i.e., bona fide) or from an artificial replica is a mandatory issue which has received a lot of attention recently. Nowadays, when the materials for the fabrication of the Presentation Attack Instruments (PAIs) have been used to train the PA Detection (PAD) methods, the PAIs can be successfully identified. However, current PAD methods still face difficulties detecting PAIs built from unknown materials or captured using other sensors. Based on that fact, we propose a new PAD technique based on three image representation approaches combining local and global information of the fingerprint. By transforming these representations into a common feature space, we can correctly discriminate bona fide from attack presentations in the aforementioned scenarios. The experimental evaluation of our proposal over the LivDet 2011 to 2015 databases, yielded error rates outperforming the top state-of-the-art results by up to 50% in the most challenging scenarios. In addition, the best configuration achieved the best results in the LivDet 2019 competition (overall accuracy of 96.17%).
Tasks
Published	2019-08-27
URL	https://arxiv.org/abs/1908.10163v1
PDF	https://arxiv.org/pdf/1908.10163v1.pdf
PWC	https://paperswithcode.com/paper/fingerprint-presentation-attack-detection-1
Repo
Framework

A streaming feature-based compression method for data from instrumented infrastructure


Title	A streaming feature-based compression method for data from instrumented infrastructure
Authors	Alastair Gregory, Din-Houn Lau, Alex Tessier, Pan Zhang
Abstract	An increasing amount of civil engineering applications are utilising data acquired from infrastructure instrumented with sensing devices. This data has an important role in monitoring the response of these structures to excitation, and evaluating structural health. In this paper we seek to monitor pedestrian-events (such as a person walking) on a footbridge using strain and acceleration data. The rate of this data acquisition and the number of sensing devices make the storage and analysis of this data a computational challenge. We introduce a streaming method to compress the sensor data, whilst preserving key patterns and features (unique to different sensor types) corresponding to pedestrian-events. Numerical demonstrations of the methodology on data obtained from strain sensors and accelerometers on the pedestrian footbridge are provided to show the trade-off between compression and accuracy during and in-between periods of pedestrian-events.
Tasks
Published	2019-04-12
URL	http://arxiv.org/abs/1904.06127v1
PDF	http://arxiv.org/pdf/1904.06127v1.pdf
PWC	https://paperswithcode.com/paper/a-streaming-feature-based-compression-method
Repo
Framework

A scalable noisy speech dataset and online subjective test framework


Title	A scalable noisy speech dataset and online subjective test framework
Authors	Chandan K. A. Reddy, Ebrahim Beyrami, Jamie Pool, Ross Cutler, Sriram Srinivasan, Johannes Gehrke
Abstract	Background noise is a major source of quality impairments in Voice over Internet Protocol (VoIP) and Public Switched Telephone Network (PSTN) calls. Recent work shows the efficacy of deep learning for noise suppression, but the datasets have been relatively small compared to those used in other domains (e.g., ImageNet) and the associated evaluations have been more focused. In order to better facilitate deep learning research in Speech Enhancement, we present a noisy speech dataset (MS-SNSD) that can scale to arbitrary sizes depending on the number of speakers, noise types, and Speech to Noise Ratio (SNR) levels desired. We show that increasing dataset sizes increases noise suppression performance as expected. In addition, we provide an open-source evaluation methodology to evaluate the results subjectively at scale using crowdsourcing, with a reference algorithm to normalize the results. To demonstrate the dataset and evaluation framework we apply it to several noise suppressors and compare the subjective Mean Opinion Score (MOS) with objective quality measures such as SNR, PESQ, POLQA, and VISQOL and show why MOS is still required. Our subjective MOS evaluation is the first large scale evaluation of Speech Enhancement algorithms that we are aware of.
Tasks	Speech Enhancement
Published	2019-09-17
URL	https://arxiv.org/abs/1909.08050v1
PDF	https://arxiv.org/pdf/1909.08050v1.pdf
PWC	https://paperswithcode.com/paper/a-scalable-noisy-speech-dataset-and-online
Repo
Framework

Soft Q-network


Title	Soft Q-network
Authors	Jingbin Liu, Xinyang Gu, Shuai Liu, Dexiang Zhang
Abstract	When DQN is announced by deepmind in 2013, the whole world is surprised by the simplicity and promising result, but due to the low efficiency and stability of this method, it is hard to solve many problems. After all these years, people purposed more and more complicated ideas for improving, many of them use distributed Deep-RL which needs tons of cores to run the simulators. However, the basic ideas behind all this technique are sometimes just a modified DQN. So we asked a simple question, is there a more elegant way to improve the DQN model? Instead of adding more and more small fixes on it, we redesign the problem setting under a popular entropy regularization framework which leads to better performance and theoretical guarantee. Finally, we purposed SQN, a new off-policy algorithm with better performance and stability.
Tasks
Published	2019-12-20
URL	https://arxiv.org/abs/1912.10891v1
PDF	https://arxiv.org/pdf/1912.10891v1.pdf
PWC	https://paperswithcode.com/paper/soft-q-network
Repo
Framework

A Nonparametric Multi-view Model for Estimating Cell Type-Specific Gene Regulatory Networks


Title	A Nonparametric Multi-view Model for Estimating Cell Type-Specific Gene Regulatory Networks
Authors	Cassandra Burdziak, Elham Azizi, Sandhya Prabhakaran, Dana Pe’er
Abstract	We present a Bayesian hierarchical multi-view mixture model termed Symphony that simultaneously learns clusters of cells representing cell types and their underlying gene regulatory networks by integrating data from two views: single-cell gene expression data and paired epigenetic data, which is informative of gene-gene interactions. This model improves interpretation of clusters as cell types with similar expression patterns as well as regulatory networks driving expression, by explaining gene-gene covariances with the biological machinery regulating gene expression. We show the theoretical advantages of the multi-view learning approach and present a Variational EM inference procedure. We demonstrate superior performance on both synthetic data and real genomic data with subtypes of peripheral blood cells compared to other methods.
Tasks	MULTI-VIEW LEARNING
Published	2019-02-21
URL	http://arxiv.org/abs/1902.08138v1
PDF	http://arxiv.org/pdf/1902.08138v1.pdf
PWC	https://paperswithcode.com/paper/a-nonparametric-multi-view-model-for
Repo
Framework

Spoken Speech Enhancement using EEG


Title	Spoken Speech Enhancement using EEG
Authors	Gautam Krishna, Co Tran, Yan Han, Mason Carnahan, Ahmed H Tewfik
Abstract	In this paper we demonstrate spoken speech enhancement using electroencephalography (EEG) signals using a generative adversarial network (GAN) based model, gated recurrent unit (GRU) regression based model, temporal convolutional network (TCN) regression model and finally using a mixed TCN GRU regression model. We compare our EEG based speech enhancement results with traditional log minimum mean-square error (MMSE) speech enhancement algorithm and our proposed methods demonstrate significant improvement in speech enhancement quality compared to the traditional method. Our overall results demonstrate that EEG features can be used to clean speech recorded in presence of background noise. To the best of our knowledge this is the first time a spoken speech enhancement is demonstrated using EEG features recorded in parallel with spoken speech.
Tasks	EEG, Speech Enhancement
Published	2019-09-13
URL	https://arxiv.org/abs/1909.09132v7
PDF	https://arxiv.org/pdf/1909.09132v7.pdf
PWC	https://paperswithcode.com/paper/spoken-speech-enhancement-using-eeg
Repo
Framework

Randomized Adversarial Imitation Learning for Autonomous Driving


Title	Randomized Adversarial Imitation Learning for Autonomous Driving
Authors	MyungJae Shin, Joongheon Kim
Abstract	With the evolution of various advanced driver assistance system (ADAS) platforms, the design of autonomous driving system is becoming more complex and safety-critical. The autonomous driving system simultaneously activates multiple ADAS functions; and thus it is essential to coordinate various ADAS functions. This paper proposes a randomized adversarial imitation learning (RAIL) method that imitates the coordination of autonomous vehicle equipped with advanced sensors. The RAIL policies are trained through derivative-free optimization for the decision maker that coordinates the proper ADAS functions, e.g., smart cruise control and lane keeping system. Especially, the proposed method is also able to deal with the LIDAR data and makes decisions in complex multi-lane highways and multi-agent environments.
Tasks	Autonomous Driving, Imitation Learning
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05637v1
PDF	https://arxiv.org/pdf/1905.05637v1.pdf
PWC	https://paperswithcode.com/paper/randomized-adversarial-imitation-learning-for
Repo
Framework