February 1, 2020

3276 words 16 mins read

Paper Group AWR 80

Hierarchical Context enabled Recurrent Neural Network for Recommendation. Convolutional Mesh Regression for Single-Image Human Shape Reconstruction. Multi-Dimension Modulation for Image Restoration with Dynamic Controllable Residual Learning. Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation. (Male, Bachelor) and …

Hierarchical Context enabled Recurrent Neural Network for Recommendation


Title	Hierarchical Context enabled Recurrent Neural Network for Recommendation
Authors	Kyungwoo Song, Mingi Ji, Sungrae Park, Il-Chul Moon
Abstract	A long user history inevitably reflects the transitions of personal interests over time. The analyses on the user history require the robust sequential model to anticipate the transitions and the decays of user interests. The user history is often modeled by various RNN structures, but the RNN structures in the recommendation system still suffer from the long-term dependency and the interest drifts. To resolve these challenges, we suggest HCRNN with three hierarchical contexts of the global, the local, and the temporary interests. This structure is designed to withhold the global long-term interest of users, to reflect the local sub-sequence interests, and to attend the temporary interests of each transition. Besides, we propose a hierarchical context-based gate structure to incorporate our \textit{interest drift assumption}. As we suggest a new RNN structure, we support HCRNN with a complementary \textit{bi-channel attention} structure to utilize hierarchical context. We experimented the suggested structure on the sequential recommendation tasks with CiteULike, MovieLens, and LastFM, and our model showed the best performances in the sequential recommendations.
Tasks
Published	2019-04-26
URL	http://arxiv.org/abs/1904.12674v1
PDF	http://arxiv.org/pdf/1904.12674v1.pdf
PWC	https://paperswithcode.com/paper/hierarchical-context-enabled-recurrent-neural
Repo	https://github.com/gtshs2/HCRNN
Framework	tf

Convolutional Mesh Regression for Single-Image Human Shape Reconstruction


Title	Convolutional Mesh Regression for Single-Image Human Shape Reconstruction
Authors	Nikos Kolotouros, Georgios Pavlakos, Kostas Daniilidis
Abstract	This paper addresses the problem of 3D human pose and shape estimation from a single image. Previous approaches consider a parametric model of the human body, SMPL, and attempt to regress the model parameters that give rise to a mesh consistent with image evidence. This parameter regression has been a very challenging task, with model-based approaches underperforming compared to nonparametric solutions in terms of pose estimation. In our work, we propose to relax this heavy reliance on the model’s parameter space. We still retain the topology of the SMPL template mesh, but instead of predicting model parameters, we directly regress the 3D location of the mesh vertices. This is a heavy task for a typical network, but our key insight is that the regression becomes significantly easier using a Graph-CNN. This architecture allows us to explicitly encode the template mesh structure within the network and leverage the spatial locality the mesh has to offer. Image-based features are attached to the mesh vertices and the Graph-CNN is responsible to process them on the mesh structure, while the regression target for each vertex is its 3D location. Having recovered the complete 3D geometry of the mesh, if we still require a specific model parametrization, this can be reliably regressed from the vertices locations. We demonstrate the flexibility and the effectiveness of our proposed graph-based mesh regression by attaching different types of features on the mesh vertices. In all cases, we outperform the comparable baselines relying on model parameter regression, while we also achieve state-of-the-art results among model-based pose estimation approaches.
Tasks	Pose Estimation
Published	2019-05-08
URL	https://arxiv.org/abs/1905.03244v1
PDF	https://arxiv.org/pdf/1905.03244v1.pdf
PWC	https://paperswithcode.com/paper/convolutional-mesh-regression-for-single
Repo	https://github.com/nkolot/GraphCMR
Framework	pytorch

Multi-Dimension Modulation for Image Restoration with Dynamic Controllable Residual Learning


Title	Multi-Dimension Modulation for Image Restoration with Dynamic Controllable Residual Learning
Authors	Jingwen He, Chao Dong, Yu Qiao
Abstract	Based on the great success of deterministic learning, to interactively control the output effects has attracted increasingly attention in the image restoration field. The goal is to generate continuous restored images by adjusting a controlling coefficient. Existing methods are restricted in realizing smooth transition between two objectives, while the real input images may contain different kinds of degradations. To make a step forward, we present a new problem called multi-dimension (MD) modulation, which aims at modulating output effects across multiple degradation types and levels. Compared with the previous single-dimension (SD) modulation, the MD task has three distinct properties, namely joint modulation, zero starting point and unbalanced learning. These obstacles motivate us to propose the first MD modulation framework – CResMD with newly introduced controllable residual connections. Specifically, we add a controlling variable on the conventional residual connection to allow a weighted summation of input and residual. The exact values of these weights are generated by a condition network. We further propose a new data sampling strategy based on beta distribution to balance different degradation types and levels. With the corrupted image and the degradation information as inputs, the network could output the corresponding restored image. By tweaking the condition vector, users are free to control the output effects in MD space at test time. Extensive experiments demonstrate that the proposed CResMD could achieve excellent performance on both SD and MD modulation tasks.
Tasks	Image Restoration
Published	2019-12-11
URL	https://arxiv.org/abs/1912.05293v1
PDF	https://arxiv.org/pdf/1912.05293v1.pdf
PWC	https://paperswithcode.com/paper/multi-dimension-modulation-for-image
Repo	https://github.com/hejingwenhejingwen/CResMD
Framework	none

Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation


Title	Detailed Human Shape Estimation from a Single Image by Hierarchical Mesh Deformation
Authors	Hao Zhu, Xinxin Zuo, Sen Wang, Xun Cao, Ruigang Yang
Abstract	This paper presents a novel framework to recover detailed human body shapes from a single image. It is a challenging task due to factors such as variations in human shapes, body poses, and viewpoints. Prior methods typically attempt to recover the human body shape using a parametric based template that lacks the surface details. As such the resulting body shape appears to be without clothing. In this paper, we propose a novel learning-based framework that combines the robustness of parametric model with the flexibility of free-form 3D deformation. We use the deep neural networks to refine the 3D shape in a Hierarchical Mesh Deformation (HMD) framework, utilizing the constraints from body joints, silhouettes, and per-pixel shading information. We are able to restore detailed human body shapes beyond skinned models. Experiments demonstrate that our method has outperformed previous state-of-the-art approaches, achieving better accuracy in terms of both 2D IoU number and 3D metric distance. The code is available in https://github.com/zhuhao-nju/hmd.git
Tasks
Published	2019-04-24
URL	https://arxiv.org/abs/1904.10506v2
PDF	https://arxiv.org/pdf/1904.10506v2.pdf
PWC	https://paperswithcode.com/paper/detailed-human-shape-estimation-from-a-single
Repo	https://github.com/zhuhao-nju/hmd
Framework	pytorch

(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas


Title	(Male, Bachelor) and (Female, Ph.D) have different connotations: Parallelly Annotated Stylistic Language Dataset with Multiple Personas
Authors	Dongyeop Kang, Varun Gangal, Eduard Hovy
Abstract	Stylistic variation in text needs to be studied with different aspects including the writer’s personal traits, interpersonal relations, rhetoric, and more. Despite recent attempts on computational modeling of the variation, the lack of parallel corpora of style language makes it difficult to systematically control the stylistic change as well as evaluate such models. We release PASTEL, the parallel and annotated stylistic language dataset, that contains ~41K parallel sentences (8.3K parallel stories) annotated across different personas. Each persona has different styles in conjunction: gender, age, country, political view, education, ethnic, and time-of-writing. The dataset is collected from human annotators with solid control of input denotation: not only preserving original meaning between text, but promoting stylistic diversity to annotators. We test the dataset on two interesting applications of style language, where PASTEL helps design appropriate experiment and evaluation. First, in predicting a target style (e.g., male or female in gender) given a text, multiple styles of PASTEL make other external style variables controlled (or fixed), which is a more accurate experimental design. Second, a simple supervised model with our parallel text outperforms the unsupervised models using nonparallel text in style transfer. Our dataset is publicly available.
Tasks	Style Transfer
Published	2019-08-31
URL	https://arxiv.org/abs/1909.00098v1
PDF	https://arxiv.org/pdf/1909.00098v1.pdf
PWC	https://paperswithcode.com/paper/male-bachelor-and-female-phd-have-different
Repo	https://github.com/dykang/PASTEL
Framework	pytorch

Supervised Symbolic Music Style Translation Using Synthetic Data


Title	Supervised Symbolic Music Style Translation Using Synthetic Data
Authors	Ondřej Cífka, Umut Şimşekli, Gaël Richard
Abstract	Research on style transfer and domain translation has clearly demonstrated the ability of deep learning-based algorithms to manipulate images in terms of artistic style. More recently, several attempts have been made to extend such approaches to music (both symbolic and audio) in order to enable transforming musical style in a similar manner. In this study, we focus on symbolic music with the goal of altering the ‘style’ of a piece while keeping its original ‘content’. As opposed to the current methods, which are inherently restricted to be unsupervised due to the lack of ‘aligned’ data (i.e. the same musical piece played in multiple styles), we develop the first fully supervised algorithm for this task. At the core of our approach lies a synthetic data generation scheme which allows us to produce virtually unlimited amounts of aligned data, and hence avoid the above issue. In view of this data generation scheme, we propose an encoder-decoder model for translating symbolic music accompaniments between a number of different styles. Our experiments show that our models, although trained entirely on synthetic data, are capable of producing musically meaningful accompaniments even for real (non-synthetic) MIDI recordings.
Tasks	Music Genre Transfer, Style Transfer, Synthetic Data Generation
Published	2019-07-04
URL	https://arxiv.org/abs/1907.02265v1
PDF	https://arxiv.org/pdf/1907.02265v1.pdf
PWC	https://paperswithcode.com/paper/supervised-symbolic-music-style-translation
Repo	https://github.com/cifkao/ismir2019-music-style-translation
Framework	none

Augmenting Neural Networks with First-order Logic


Title	Augmenting Neural Networks with First-order Logic
Authors	Tao Li, Vivek Srikumar
Abstract	Today, the dominant paradigm for training neural networks involves minimizing task loss on a large dataset. Using world knowledge to inform a model, and yet retain the ability to perform end-to-end training remains an open question. In this paper, we present a novel framework for introducing declarative knowledge to neural network architectures in order to guide training and prediction. Our framework systematically compiles logical statements into computation graphs that augment a neural network without extra learnable parameters or manual redesign. We evaluate our modeling strategy on three tasks: machine comprehension, natural language inference, and text chunking. Our experiments show that knowledge-augmented networks can strongly improve over baselines, especially in low-data regimes.
Tasks	Chunking, Natural Language Inference, Reading Comprehension
Published	2019-06-14
URL	https://arxiv.org/abs/1906.06298v2
PDF	https://arxiv.org/pdf/1906.06298v2.pdf
PWC	https://paperswithcode.com/paper/augmenting-neural-networks-with-first-order
Repo	https://github.com/utahnlp/layer_augmentation
Framework	pytorch

Deep Recurrent Quantization for Generating Sequential Binary Codes


Title	Deep Recurrent Quantization for Generating Sequential Binary Codes
Authors	Jingkuan Song, Xiaosu Zhu, Lianli Gao, Xin-Shun Xu, Wu Liu, Heng Tao Shen
Abstract	Quantization has been an effective technology in ANN (approximate nearest neighbour) search due to its high accuracy and fast search speed. To meet the requirement of different applications, there is always a trade-off between retrieval accuracy and speed, reflected by variable code lengths. However, to encode the dataset into different code lengths, existing methods need to train several models, where each model can only produce a specific code length. This incurs a considerable training time cost, and largely reduces the flexibility of quantization methods to be deployed in real applications. To address this issue, we propose a Deep Recurrent Quantization (DRQ) architecture which can generate sequential binary codes. To the end, when the model is trained, a sequence of binary codes can be generated and the code length can be easily controlled by adjusting the number of recurrent iterations. A shared codebook and a scalar factor is designed to be the learnable weights in the deep recurrent quantization block, and the whole framework can be trained in an end-to-end manner. As far as we know, this is the first quantization method that can be trained once and generate sequential binary codes. Experimental results on the benchmark datasets show that our model achieves comparable or even better performance compared with the state-of-the-art for image retrieval. But it requires significantly less number of parameters and training times. Our code is published online: https://github.com/cfm-uestc/DRQ.
Tasks	Image Retrieval, Quantization
Published	2019-06-16
URL	https://arxiv.org/abs/1906.06699v2
PDF	https://arxiv.org/pdf/1906.06699v2.pdf
PWC	https://paperswithcode.com/paper/deep-recurrent-quantization-for-generating
Repo	https://github.com/cfm-uestc/DRQ
Framework	tf

Neural Entropic Estimation: A faster path to mutual information estimation


Title	Neural Entropic Estimation: A faster path to mutual information estimation
Authors	Chung Chan, Ali Al-Bashabsheh, Hing Pang Huang, Michael Lim, Da Sun Handason Tam, Chao Zhao
Abstract	We point out a limitation of the mutual information neural estimation (MINE) where the network fails to learn at the initial training phase, leading to slow convergence in the number of training iterations. To solve this problem, we propose a faster method called the mutual information neural entropic estimation (MI-NEE). Our solution first generalizes MINE to estimate the entropy using a custom reference distribution. The entropy estimate can then be used to estimate the mutual information. We argue that the seemingly redundant intermediate step of entropy estimation allows one to improve the convergence by an appropriate reference distribution. In particular, we show that MI-NEE reduces to MINE in the special case when the reference distribution is the product of marginal distributions, but faster convergence is possible by choosing the uniform distribution as the reference distribution instead. Compared to the product of marginals, the uniform distribution introduces more samples in low-density regions and fewer samples in high-density regions, which appear to lead to an overall larger gradient for faster convergence.
Tasks
Published	2019-05-30
URL	https://arxiv.org/abs/1905.12957v2
PDF	https://arxiv.org/pdf/1905.12957v2.pdf
PWC	https://paperswithcode.com/paper/neural-entropic-estimation-a-faster-path-to
Repo	https://github.com/ccha23/MI-NEE
Framework	pytorch

Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation


Title	Detect Camouflaged Spam Content via StoneSkipping: Graph and Text Joint Embedding for Chinese Character Variation Representation
Authors	Zhuoren Jiang, Zhe Gao, Guoxiu He, Yangyang Kang, Changlong Sun, Qiong Zhang, Luo Si, Xiaozhong Liu
Abstract	The task of Chinese text spam detection is very challenging due to both glyph and phonetic variations of Chinese characters. This paper proposes a novel framework to jointly model Chinese variational, semantic, and contextualized representations for Chinese text spam detection task. In particular, a Variation Family-enhanced Graph Embedding (VFGE) algorithm is designed based on a Chinese character variation graph. The VFGE can learn both the graph embeddings of the Chinese characters (local) and the latent variation families (global). Furthermore, an enhanced bidirectional language model, with a combination gate function and an aggregation learning function, is proposed to integrate the graph and text information while capturing the sequential information. Extensive experiments have been conducted on both SMS and review datasets, to show the proposed method outperforms a series of state-of-the-art models for Chinese spam detection.
Tasks	Graph Embedding, Language Modelling
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11561v1
PDF	https://arxiv.org/pdf/1908.11561v1.pdf
PWC	https://paperswithcode.com/paper/detect-camouflaged-spam-content-via
Repo	https://github.com/Giruvegan/stoneskipping
Framework	none

Challenges of Real-World Reinforcement Learning


Title	Challenges of Real-World Reinforcement Learning
Authors	Gabriel Dulac-Arnold, Daniel Mankowitz, Todd Hester
Abstract	Reinforcement learning (RL) has proven its worth in a series of artificial domains, and is beginning to show some successes in real-world scenarios. However, much of the research advances in RL are often hard to leverage in real-world systems due to a series of assumptions that are rarely satisfied in practice. We present a set of nine unique challenges that must be addressed to productionize RL to real world problems. For each of these challenges, we specify the exact meaning of the challenge, present some approaches from the literature, and specify some metrics for evaluating that challenge. An approach that addresses all nine challenges would be applicable to a large number of real world problems. We also present an example domain that has been modified to present these challenges as a testbed for practical RL research.
Tasks
Published	2019-04-29
URL	http://arxiv.org/abs/1904.12901v1
PDF	http://arxiv.org/pdf/1904.12901v1.pdf
PWC	https://paperswithcode.com/paper/challenges-of-real-world-reinforcement
Repo	https://github.com/google-research/realworldrl_suite
Framework	tf

Evaluating Language Model Finetuning Techniques for Low-resource Languages


Title	Evaluating Language Model Finetuning Techniques for Low-resource Languages
Authors	Jan Christian Blaise Cruz, Charibeth Cheng
Abstract	Unlike mainstream languages (such as English and French), low-resource languages often suffer from a lack of expert-annotated corpora and benchmark resources that make it hard to apply state-of-the-art techniques directly. In this paper, we alleviate this scarcity problem for the low-resourced Filipino language in two ways. First, we introduce a new benchmark language modeling dataset in Filipino which we call WikiText-TL-39. Second, we show that language model finetuning techniques such as BERT and ULMFiT can be used to consistently train robust classifiers in low-resource settings, experiencing at most a 0.0782 increase in validation error when the number of training examples is decreased from 10K to 1K while finetuning using a privately-held sentiment dataset.
Tasks	Language Modelling
Published	2019-06-30
URL	https://arxiv.org/abs/1907.00409v1
PDF	https://arxiv.org/pdf/1907.00409v1.pdf
PWC	https://paperswithcode.com/paper/evaluating-language-model-finetuning
Repo	https://github.com/jcblaisecruz02/Tagalog-BERT
Framework	pytorch

A probability theoretic approach to drifting data in continuous time domains


Title	A probability theoretic approach to drifting data in continuous time domains
Authors	Fabian Hinder, André Artelt, Barbara Hammer
Abstract	The notion of drift refers to the phenomenon that the distribution, which is underlying the observed data, changes over time. Albeit many attempts were made to deal with drift, formal notions of drift are application-dependent and formulated in various degrees of abstraction and mathematical coherence. In this contribution, we provide a probability theoretical framework, that allows a formalization of drift in continuous time, which subsumes popular notions of drift. In particular, it sheds some light on common practice such as change-point detection or machine learning methodologies in the presence of drift. It gives rise to a new characterization of drift in terms of stochastic dependency between data and time. This particularly intuitive formalization enables us to design a new, efficient drift detection method. Further, it induces a technology, to decompose observed data into a drifting and a non-drifting part.
Tasks	Change Point Detection
Published	2019-12-04
URL	https://arxiv.org/abs/1912.01969v1
PDF	https://arxiv.org/pdf/1912.01969v1.pdf
PWC	https://paperswithcode.com/paper/a-probability-theoretic-approach-to-drifting
Repo	https://github.com/FabianHinder/drifting-data-in-continuous-time
Framework	none

Invertible generative models for inverse problems: mitigating representation error and dataset bias


Title	Invertible generative models for inverse problems: mitigating representation error and dataset bias
Authors	Muhammad Asim, Ali Ahmed, Paul Hand
Abstract	Trained generative models have shown remarkable performance as priors for inverse problems in imaging. For example, Generative Adversarial Network priors permit recovery of test images from 5-10x fewer measurements than sparsity priors. Unfortunately, these models may be unable to represent any particular image because of architectural choices, mode collapse, and bias in the training dataset. In this paper, we demonstrate that invertible neural networks, which have zero representation error by design, can be effective natural signal priors at inverse problems such as denoising, compressive sensing, and inpainting. Our formulation is an empirical risk minimization that does not directly optimize the likelihood of images, as one would expect. Instead we optimize the likelihood of the latent representation of images as a proxy, as this is empirically easier. For compressive sensing, our formulation can yield higher accuracy than sparsity priors across almost all undersampling ratios. For the same accuracy on test images, they can use 10-20x fewer measurements. We demonstrate that invertible priors can yield better reconstructions than sparsity priors for images that have rare features of variation within the biased training set, including out-of-distribution natural images.
Tasks	Compressive Sensing, Denoising
Published	2019-05-28
URL	https://arxiv.org/abs/1905.11672v3
PDF	https://arxiv.org/pdf/1905.11672v3.pdf
PWC	https://paperswithcode.com/paper/invertible-generative-models-for-inverse
Repo	https://github.com/CACTuS-AI/GlowIP
Framework	pytorch

Plug-and-Play Methods Provably Converge with Properly Trained Denoisers


Title	Plug-and-Play Methods Provably Converge with Properly Trained Denoisers
Authors	Ernest K. Ryu, Jialin Liu, Sicheng Wang, Xiaohan Chen, Zhangyang Wang, Wotao Yin
Abstract	Plug-and-play (PnP) is a non-convex framework that integrates modern denoising priors, such as BM3D or deep learning-based denoisers, into ADMM or other proximal algorithms. An advantage of PnP is that one can use pre-trained denoisers when there is not sufficient data for end-to-end training. Although PnP has been recently studied extensively with great empirical success, theoretical analysis addressing even the most basic question of convergence has been insufficient. In this paper, we theoretically establish convergence of PnP-FBS and PnP-ADMM, without using diminishing stepsizes, under a certain Lipschitz condition on the denoisers. We then propose real spectral normalization, a technique for training deep learning-based denoisers to satisfy the proposed Lipschitz condition. Finally, we present experimental results validating the theory.
Tasks	Denoising
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05406v1
PDF	https://arxiv.org/pdf/1905.05406v1.pdf
PWC	https://paperswithcode.com/paper/plug-and-play-methods-provably-converge-with
Repo	https://github.com/uclaopt/Provable_Plug_and_Play
Framework	pytorch