February 1, 2020

3185 words 15 mins read

Paper Group AWR 300

Label Embedded Dictionary Learning for Image Classification. Content Differences in Syntactic and Semantic Representations. A Deep Generative Model for Graph Layout. Mining Discourse Markers for Unsupervised Sentence Representation Learning. Re-examination of the Role of Latent Variables in Sequence Modeling. A Multi-task Learning Model for Chinese …

Label Embedded Dictionary Learning for Image Classification


Title	Label Embedded Dictionary Learning for Image Classification
Authors	Shuai Shao, Yan-Jiang Wang, Bao-Di Liu, Weifeng Liu, Rui Xu
Abstract	Recently, label consistent k-svd (LC-KSVD) algorithm has been successfully applied in image classification. The objective function of LC-KSVD is consisted of reconstruction error, classification error and discriminative sparse codes error with L0-norm sparse regularization term. The L0-norm, however, leads to NP-hard problem. Despite some methods such as orthogonal matching pursuit can help solve this problem to some extent, it is quite difficult to find the optimum sparse solution. To overcome this limitation, we propose a label embedded dictionary learning (LEDL) method to utilise the L1-norm as the sparse regularization term so that we can avoid the hard-to-optimize problem by solving the convex optimization problem. Alternating direction method of multipliers and blockwise coordinate descent algorithm are then exploited to optimize the corresponding objective function. Extensive experimental results on six benchmark datasets illustrate that the proposed algorithm has achieved superior performance compared to some conventional classification algorithms.
Tasks	Dictionary Learning, Image Classification
Published	2019-03-07
URL	http://arxiv.org/abs/1903.03087v2
PDF	http://arxiv.org/pdf/1903.03087v2.pdf
PWC	https://paperswithcode.com/paper/label-embedded-dictionary-learning-for-image
Repo	https://github.com/The-Shuai/Label-Embedded-Dictionary-Learning
Framework	none

Content Differences in Syntactic and Semantic Representations


Title	Content Differences in Syntactic and Semantic Representations
Authors	Daniel Hershcovich, Omri Abend, Ari Rappoport
Abstract	Syntactic analysis plays an important role in semantic parsing, but the nature of this role remains a topic of ongoing debate. The debate has been constrained by the scarcity of empirical comparative studies between syntactic and semantic schemes, which hinders the development of parsing methods informed by the details of target schemes and constructions. We target this gap, and take Universal Dependencies (UD) and UCCA as a test case. After abstracting away from differences of convention or formalism, we find that most content divergences can be ascribed to: (1) UCCA’s distinction between a Scene and a non-Scene; (2) UCCA’s distinction between primary relations, secondary ones and participants; (3) different treatment of multi-word expressions, and (4) different treatment of inter-clause linkage. We further discuss the long tail of cases where the two schemes take markedly different approaches. Finally, we show that the proposed comparison methodology can be used for fine-grained evaluation of UCCA parsing, highlighting both challenges and potential sources for improvement. The substantial differences between the schemes suggest that semantic parsers are likely to benefit downstream text understanding applications beyond their syntactic counterparts.
Tasks	Semantic Parsing
Published	2019-03-15
URL	http://arxiv.org/abs/1903.06494v5
PDF	http://arxiv.org/pdf/1903.06494v5.pdf
PWC	https://paperswithcode.com/paper/content-differences-in-syntactic-and-semantic
Repo	https://github.com/danielhers/synsem
Framework	none

A Deep Generative Model for Graph Layout


Title	A Deep Generative Model for Graph Layout
Authors	Oh-Hyun Kwon, Kwan-Liu Ma
Abstract	Different layouts can characterize different aspects of the same graph. Finding a “good” layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-and-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.
Tasks
Published	2019-04-27
URL	https://arxiv.org/abs/1904.12225v7
PDF	https://arxiv.org/pdf/1904.12225v7.pdf
PWC	https://paperswithcode.com/paper/a-deep-generative-model-for-graph-layout
Repo	https://github.com/preddy5/A-Deep-Generative-Model-for-Graph-Layout
Framework	pytorch

Mining Discourse Markers for Unsupervised Sentence Representation Learning


Title	Mining Discourse Markers for Unsupervised Sentence Representation Learning
Authors	Damien Sileo, Tim Van-De-Cruys, Camille Pradel, Philippe Muller
Abstract	Current state of the art systems in NLP heavily rely on manually annotated datasets, which are expensive to construct. Very little work adequately exploits unannotated data – such as discourse markers between sentences – mainly because of data sparseness and ineffective extraction methods. In the present work, we propose a method to automatically discover sentence pairs with relevant discourse markers, and apply it to massive amounts of data. Our resulting dataset contains 174 discourse markers with at least 10k examples each, even for rare markers such as coincidentally or amazingly We use the resulting data as supervision for learning transferable sentence embeddings. In addition, we show that even though sentence representation learning through prediction of discourse markers yields state of the art results across different transfer tasks, it is not clear that our models made use of the semantic relation between sentences, thus leaving room for further improvements. Our datasets are publicly available (https://github.com/synapse-developpement/Discovery)
Tasks	Representation Learning, Sentence Embeddings
Published	2019-03-28
URL	http://arxiv.org/abs/1903.11850v1
PDF	http://arxiv.org/pdf/1903.11850v1.pdf
PWC	https://paperswithcode.com/paper/mining-discourse-markers-for-unsupervised
Repo	https://github.com/synapse-developpement/Discovery
Framework	none

Re-examination of the Role of Latent Variables in Sequence Modeling


Title	Re-examination of the Role of Latent Variables in Sequence Modeling
Authors	Zihang Dai, Guokun Lai, Yiming Yang, Shinjae Yoo
Abstract	With latent variables, stochastic recurrent models have achieved state-of-the-art performance in modeling sound-wave sequence. However, opposite results are also observed in other domains, where standard recurrent networks often outperform stochastic models. To better understand this discrepancy, we re-examine the roles of latent variables in stochastic recurrent models for speech density estimation. Our analysis reveals that under the restriction of fully factorized output distribution in previous evaluations, the stochastic models were implicitly leveraging intra-step correlation but the standard recurrent baselines were prohibited to do so, resulting in an unfair comparison. To correct the unfairness, we remove such restriction in our re-examination, where all the models can explicitly leverage intra-step correlation with an auto-regressive structure. Over a diverse set of sequential data, including human speech, MIDI music, handwriting trajectory and frame-permuted speech, our results show that stochastic recurrent models fail to exhibit any practical advantage despite the claimed theoretical superiority. In contrast, standard recurrent models equipped with an auto-regressive output distribution consistently perform better, significantly advancing the state-of-the-art results on three speech datasets.
Tasks	Density Estimation
Published	2019-02-04
URL	https://arxiv.org/abs/1902.01388v2
PDF	https://arxiv.org/pdf/1902.01388v2.pdf
PWC	https://paperswithcode.com/paper/re-examination-of-the-role-of-latent
Repo	https://github.com/zihangdai/reexamine-srnn
Framework	pytorch

A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction


Title	A Multi-task Learning Model for Chinese-oriented Aspect Polarity Classification and Aspect Term Extraction
Authors	Heng Yang, Biqing Zeng, JianHao Yang, Youwei Song, Ruyang Xu
Abstract	Aspect-based sentiment analysis (ABSA) task is a multi-grained task of natural language processing and consists of two subtasks: aspect term extraction (ATE) and aspect polarity classification (APC). Most of the existing work focuses on the subtask of aspect term polarity inferring and ignores the significance of aspect term extraction. Besides, the existing researches do not pay attention to the research of the Chinese-oriented ABSA task. Based on the local context focus (LCF) mechanism, this paper firstly proposes a multi-task learning model for Chinese-oriented aspect-based sentiment analysis, namely LCF-ATEPC. Compared with existing models, this model equips the capability of extracting aspect term and inferring aspect term polarity synchronously, moreover, this model is effective to analyze both Chinese and English comments simultaneously and the experiment on a multilingual mixed dataset proved its availability. By integrating the domain-adapted BERT model, the LCF-ATEPC model achieved the state-of-the-art performance of aspect term extraction and aspect polarity classification in four Chinese review datasets. Besides, the experimental results on the most commonly used SemEval-2014 task4 Restaurant and Laptop datasets outperform the state-of-the-art performance on the ATE and APC subtask.
Tasks	Aspect-Based Sentiment Analysis, Multi-Task Learning, Sentiment Analysis
Published	2019-12-17
URL	https://arxiv.org/abs/1912.07976v3
PDF	https://arxiv.org/pdf/1912.07976v3.pdf
PWC	https://paperswithcode.com/paper/a-multi-task-learning-model-for-chinese
Repo	https://github.com/yangheng95/LCF-ATEPC
Framework	pytorch

On the Difficulty of Evaluating Baselines: A Study on Recommender Systems


Title	On the Difficulty of Evaluating Baselines: A Study on Recommender Systems
Authors	Steffen Rendle, Li Zhang, Yehuda Koren
Abstract	Numerical evaluations with comparisons to baselines play a central role when judging research in recommender systems. In this paper, we show that running baselines properly is difficult. We demonstrate this issue on two extensively studied datasets. First, we show that results for baselines that have been used in numerous publications over the past five years for the Movielens 10M benchmark are suboptimal. With a careful setup of a vanilla matrix factorization baseline, we are not only able to improve upon the reported results for this baseline but even outperform the reported results of any newly proposed method. Secondly, we recap the tremendous effort that was required by the community to obtain high quality results for simple methods on the Netflix Prize. Our results indicate that empirical findings in research papers are questionable unless they were obtained on standardized benchmarks where baselines have been tuned extensively by the research community.
Tasks	Recommendation Systems
Published	2019-05-04
URL	https://arxiv.org/abs/1905.01395v1
PDF	https://arxiv.org/pdf/1905.01395v1.pdf
PWC	https://paperswithcode.com/paper/on-the-difficulty-of-evaluating-baselines-a
Repo	https://github.com/srendle/libfm
Framework	none

Theoretical evidence for adversarial robustness through randomization


Title	Theoretical evidence for adversarial robustness through randomization
Authors	Rafael Pinot, Laurent Meunier, Alexandre Araujo, Hisashi Kashima, Florian Yger, Cédric Gouy-Pailler, Jamal Atif
Abstract	This paper investigates the theory of robustness against adversarial attacks. It focuses on the family of randomization techniques that consist in injecting noise in the network at inference time. These techniques have proven effective in many contexts, but lack theoretical arguments. We close this gap by presenting a theoretical analysis of these approaches, hence explaining why they perform well in practice. More precisely, we make two new contributions. The first one relates the randomization rate to robustness to adversarial attacks. This result applies for the general family of exponential distributions, and thus extends and unifies the previous approaches. The second contribution consists in devising a new upper bound on the adversarial generalization gap of randomized neural networks. We support our theoretical claims with a set of experiments.
Tasks
Published	2019-02-04
URL	https://arxiv.org/abs/1902.01148v2
PDF	https://arxiv.org/pdf/1902.01148v2.pdf
PWC	https://paperswithcode.com/paper/theoretical-evidence-for-adversarial
Repo	https://github.com/MILES-PSL/Adversarial-Robustness-Through-Randomization
Framework	tf

4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks


Title	4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
Authors	Christopher Choy, JunYoung Gwak, Silvio Savarese
Abstract	In many robotics and VR/AR applications, 3D-videos are readily-available sources of input (a continuous sequence of depth images, or LIDAR scans). However, those 3D-videos are processed frame-by-frame either through 2D convnets or 3D perception algorithms. In this work, we propose 4-dimensional convolutional neural networks for spatio-temporal perception that can directly process such 3D-videos using high-dimensional convolutions. For this, we adopt sparse tensors and propose the generalized sparse convolution that encompasses all discrete convolutions. To implement the generalized sparse convolution, we create an open-source auto-differentiation library for sparse tensors that provides extensive functions for high-dimensional convolutional neural networks. We create 4D spatio-temporal convolutional neural networks using the library and validate them on various 3D semantic segmentation benchmarks and proposed 4D datasets for 3D-video perception. To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal consistency in the 7D space-time-chroma space. Experimentally, we show that convolutional neural networks with only generalized 3D sparse convolutions can outperform 2D or 2D-3D hybrid methods by a large margin. Also, we show that on 3D-videos, 4D spatio-temporal convolutional neural networks are robust to noise, outperform 3D convolutional neural networks and are faster than the 3D counterpart in some cases.
Tasks	3D Semantic Segmentation, 4D Spatio Temporal Semantic Segmentation, Semantic Segmentation
Published	2019-04-18
URL	https://arxiv.org/abs/1904.08755v4
PDF	https://arxiv.org/pdf/1904.08755v4.pdf
PWC	https://paperswithcode.com/paper/4d-spatio-temporal-convnets-minkowski
Repo	https://github.com/StanfordVL/MinkowskiEngine
Framework	pytorch

O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks


Title	O-GAN: Extremely Concise Approach for Auto-Encoding Generative Adversarial Networks
Authors	Jianlin Su
Abstract	In this paper, we propose Orthogonal Generative Adversarial Networks (O-GANs). We decompose the network of discriminator orthogonally and add an extra loss into the objective of common GANs, which can enforce discriminator become an effective encoder. The same extra loss can be embedded into any kind of GANs and there is almost no increase in computation. Furthermore, we discuss the principle of our method, which is relative to the fully-exploiting of the remaining degrees of freedom of discriminator. As we know, our solution is the simplest approach to train a generative adversarial network with auto-encoding ability.
Tasks
Published	2019-03-05
URL	http://arxiv.org/abs/1903.01931v1
PDF	http://arxiv.org/pdf/1903.01931v1.pdf
PWC	https://paperswithcode.com/paper/o-gan-extremely-concise-approach-for-auto
Repo	https://github.com/bojone/o-gan
Framework	tf

Interpolation-Prediction Networks for Irregularly Sampled Time Series


Title	Interpolation-Prediction Networks for Irregularly Sampled Time Series
Authors	Satya Narayan Shukla, Benjamin M. Marlin
Abstract	In this paper, we present a new deep learning architecture for addressing the problem of supervised learning with sparse and irregularly sampled multivariate time series. The architecture is based on the use of a semi-parametric interpolation network followed by the application of a prediction network. The interpolation network allows for information to be shared across multiple dimensions of a multivariate time series during the interpolation stage, while any standard deep learning model can be used for the prediction network. This work is motivated by the analysis of physiological time series data in electronic health records, which are sparse, irregularly sampled, and multivariate. We investigate the performance of this architecture on both classification and regression tasks, showing that our approach outperforms a range of baseline and recently proposed models.
Tasks	Length-of-Stay prediction, Mortality Prediction, Time Series
Published	2019-09-13
URL	https://arxiv.org/abs/1909.07782v1
PDF	https://arxiv.org/pdf/1909.07782v1.pdf
PWC	https://paperswithcode.com/paper/interpolation-prediction-networks-for-1
Repo	https://github.com/mlds-lab/interp-net
Framework	tf

On the Variance of the Adaptive Learning Rate and Beyond


Title	On the Variance of the Adaptive Learning Rate and Beyond
Authors	Liyuan Liu, Haoming Jiang, Pengcheng He, Weizhu Chen, Xiaodong Liu, Jianfeng Gao, Jiawei Han
Abstract	The learning rate warmup heuristic achieves remarkable success in stabilizing training, accelerating convergence and improving generalization for adaptive stochastic optimization algorithms like RMSprop and Adam. Here, we study its mechanism in details. Pursuing the theory behind warmup, we identify a problem of the adaptive learning rate (i.e., it has problematically large variance in the early stage), suggest warmup works as a variance reduction technique, and provide both empirical and theoretical evidence to verify our hypothesis. We further propose RAdam, a new variant of Adam, by introducing a term to rectify the variance of the adaptive learning rate. Extensive experimental results on image classification, language modeling, and neural machine translation verify our intuition and demonstrate the effectiveness and robustness of our proposed method. All implementations are available at: https://github.com/LiyuanLucasLiu/RAdam.
Tasks	Image Classification, Language Modelling, Machine Translation, Stochastic Optimization
Published	2019-08-08
URL	https://arxiv.org/abs/1908.03265v2
PDF	https://arxiv.org/pdf/1908.03265v2.pdf
PWC	https://paperswithcode.com/paper/on-the-variance-of-the-adaptive-learning-rate
Repo	https://github.com/float256/rectified-adam-keras
Framework	tf

Data-Free Point Cloud Network for 3D Face Recognition


Title	Data-Free Point Cloud Network for 3D Face Recognition
Authors	Ziyu, Zhang, Feipeng, Da, Yi, Yu
Abstract	Point clouds-based Networks have achieved great attention in 3D object classification, segmentation and indoor scene semantic parsing. In terms of face recognition, 3D face recognition method which directly consume point clouds as input is still under study. Two main factors account for this: One is how to get discriminative face representations from 3D point clouds using deep network; the other is the lack of large 3D training dataset. To address these problems, a data-free 3D face recognition method is proposed only using synthesized unreal data from statistical 3D Morphable Model to train a deep point cloud network. To ease the inconsistent distribution between model data and real faces, different point sampling methods are used in train and test phase. In this paper, we propose a curvature-aware point sampling(CPS) strategy replacing the original furthest point sampling(FPS) to hierarchically down-sample feature-sensitive points which are crucial to pass and aggregate features deeply. A PointNet++ like Network is used to extract face features directly from point clouds. The experimental results show that the network trained on generated data generalizes well for real 3D faces. Fine tuning on a small part of FRGCv2.0 and Bosphorus, which include real faces in different poses and expressions, further improves recognition accuracy.
Tasks	3D Object Classification, Face Recognition, Object Classification, Semantic Parsing
Published	2019-11-12
URL	https://arxiv.org/abs/1911.04731v1
PDF	https://arxiv.org/pdf/1911.04731v1.pdf
PWC	https://paperswithcode.com/paper/data-free-point-cloud-network-for-3d-face
Repo	https://github.com/alfredtorres/3DFacePointCloudNet
Framework	pytorch

NeurVPS: Neural Vanishing Point Scanning via Conic Convolution


Title	NeurVPS: Neural Vanishing Point Scanning via Conic Convolution
Authors	Yichao Zhou, Haozhi Qi, Jingwei Huang, Yi Ma
Abstract	We present a simple yet effective end-to-end trainable deep network with geometry-inspired convolutional operators for detecting vanishing points in images. Traditional convolutional neural networks rely on aggregating edge features and do not have mechanisms to directly exploit the geometric properties of vanishing points as the intersections of parallel lines. In this work, we identify a canonical conic space in which the neural network can effectively compute the global geometric information of vanishing points locally, and we propose a novel operator named conic convolution that can be implemented as regular convolutions in this space. This new operator explicitly enforces feature extractions and aggregations along the structural lines and yet has the same number of parameters as the regular 2D convolution. Our extensive experiments on both synthetic and real-world datasets show that the proposed operator significantly improves the performance of vanishing point detection over traditional methods. The code and dataset have been made publicly available at https://github.com/zhou13/neurvps.
Tasks
Published	2019-10-14
URL	https://arxiv.org/abs/1910.06316v2
PDF	https://arxiv.org/pdf/1910.06316v2.pdf
PWC	https://paperswithcode.com/paper/neurvps-neural-vanishing-point-scanning-via
Repo	https://github.com/zhou13/neurvps
Framework	pytorch

Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning


Title	Heavy Rain Image Restoration: Integrating Physics Model and Conditional Adversarial Learning
Authors	Ruotent Li, Loong Fah Cheong, Robby T. Tan
Abstract	Most deraining works focus on rain streaks removal but they cannot deal adequately with heavy rain images. In heavy rain, streaks are strongly visible, dense rain accumulation or rain veiling effect significantly washes out the image, further scenes are relatively more blurry, etc. In this paper, we propose a novel method to address these problems. We put forth a 2-stage network: a physics-based backbone followed by a depth-guided GAN refinement. The first stage estimates the rain streaks, the transmission, and the atmospheric light governed by the underlying physics. To tease out these components more reliably, a guided filtering framework is used to decompose the image into its low- and high-frequency components. This filtering is guided by a rain-free residue image — its content is used to set the passbands for the two channels in a spatially-variant manner so that the background details do not get mixed up with the rain-streaks. For the second stage, the refinement stage, we put forth a depth-guided GAN to recover the background details failed to be retrieved by the first stage, as well as correcting artefacts introduced by that stage. We have evaluated our method against the state of the art methods. Extensive experiments show that our method outperforms them on real rain image data, recovering visually clean images with good details.
Tasks	Image Restoration, Rain Removal
Published	2019-04-10
URL	http://arxiv.org/abs/1904.05050v1
PDF	http://arxiv.org/pdf/1904.05050v1.pdf
PWC	https://paperswithcode.com/paper/heavy-rain-image-restoration-integrating
Repo	https://github.com/liruoteng/HeavyRainRemoval
Framework	pytorch