July 29, 2019

2993 words 15 mins read

Paper Group AWR 81

Learning More Universal Representations for Transfer-Learning. Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models. Deep Competitive Pathway Networks. One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay. The Code2Text Challenge: Text Genera …

Learning More Universal Representations for Transfer-Learning


Title	Learning More Universal Representations for Transfer-Learning
Authors	Youssef Tamaazousti, Hervé Le Borgne, Céline Hudelot, Mohamed El Amine Seddik, Mohamed Tamaazousti
Abstract	A representation is supposed universal if it encodes any element of the visual world (e.g., objects, scenes) in any configuration (e.g., scale, context). While not expecting pure universal representations, the goal in the literature is to improve the universality level, starting from a representation with a certain level. To do so, the state-of-the-art consists in learning CNN-based representations on a diversified training problem (e.g., ImageNet modified by adding annotated data). While it effectively increases universality, such approach still requires a large amount of efforts to satisfy the needs in annotated data. In this work, we propose two methods to improve universality, but pay special attention to limit the need of annotated data. We also propose a unified framework of the methods based on the diversifying of the training problem. Finally, to better match Atkinson’s cognitive study about universal human representations, we proposed to rely on the transfer-learning scheme as well as a new metric to evaluate universality. This latter, aims us to demonstrates the interest of our methods on 10 target-problems, relating to the classification task and a variety of visual domains.
Tasks	Transfer Learning
Published	2017-12-27
URL	http://arxiv.org/abs/1712.09708v5
PDF	http://arxiv.org/pdf/1712.09708v5.pdf
PWC	https://paperswithcode.com/paper/learning-more-universal-representations-for
Repo	https://github.com/youssefTamaazousti/MulDiPNet
Framework	tf

Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models


Title	Conjugate-Computation Variational Inference : Converting Variational Inference in Non-Conjugate Models to Inferences in Conjugate Models
Authors	Mohammad Emtiyaz Khan, Wu Lin
Abstract	Variational inference is computationally challenging in models that contain both conjugate and non-conjugate terms. Methods specifically designed for conjugate models, even though computationally efficient, find it difficult to deal with non-conjugate terms. On the other hand, stochastic-gradient methods can handle the non-conjugate terms but they usually ignore the conjugate structure of the model which might result in slow convergence. In this paper, we propose a new algorithm called Conjugate-computation Variational Inference (CVI) which brings the best of the two worlds together – it uses conjugate computations for the conjugate terms and employs stochastic gradients for the rest. We derive this algorithm by using a stochastic mirror-descent method in the mean-parameter space, and then expressing each gradient step as a variational inference in a conjugate model. We demonstrate our algorithm’s applicability to a large class of models and establish its convergence. Our experimental results show that our method converges much faster than the methods that ignore the conjugate structure of the model.
Tasks
Published	2017-03-13
URL	http://arxiv.org/abs/1703.04265v2
PDF	http://arxiv.org/pdf/1703.04265v2.pdf
PWC	https://paperswithcode.com/paper/conjugate-computation-variational-inference
Repo	https://github.com/vmasrani/CVI_PLDS
Framework	none

Deep Competitive Pathway Networks


Title	Deep Competitive Pathway Networks
Authors	Jia-Ren Chang, Yong-Sheng Chen
Abstract	In the design of deep neural architectures, recent studies have demonstrated the benefits of grouping subnetworks into a larger network. For examples, the Inception architecture integrates multi-scale subnetworks and the residual network can be regarded that a residual unit combines a residual subnetwork with an identity shortcut. In this work, we embrace this observation and propose the Competitive Pathway Network (CoPaNet). The CoPaNet comprises a stack of competitive pathway units and each unit contains multiple parallel residual-type subnetworks followed by a max operation for feature competition. This mechanism enhances the model capability by learning a variety of features in subnetworks. The proposed strategy explicitly shows that the features propagate through pathways in various routing patterns, which is referred to as pathway encoding of category information. Moreover, the cross-block shortcut can be added to the CoPaNet to encourage feature reuse. We evaluated the proposed CoPaNet on four object recognition benchmarks: CIFAR-10, CIFAR-100, SVHN, and ImageNet. CoPaNet obtained the state-of-the-art or comparable results using similar amounts of parameters. The code of CoPaNet is available at: https://github.com/JiaRenChang/CoPaNet.
Tasks	Image Classification, Object Recognition
Published	2017-09-29
URL	http://arxiv.org/abs/1709.10282v1
PDF	http://arxiv.org/pdf/1709.10282v1.pdf
PWC	https://paperswithcode.com/paper/deep-competitive-pathway-networks
Repo	https://github.com/JiaRenChang/CoPaNet
Framework	torch


Title	One-Shot Reinforcement Learning for Robot Navigation with Interactive Replay
Authors	Jake Bruce, Niko Suenderhauf, Piotr Mirowski, Raia Hadsell, Michael Milford
Abstract	Recently, model-free reinforcement learning algorithms have been shown to solve challenging problems by learning from extensive interaction with the environment. A significant issue with transferring this success to the robotics domain is that interaction with the real world is costly, but training on limited experience is prone to overfitting. We present a method for learning to navigate, to a fixed goal and in a known environment, on a mobile robot. The robot leverages an interactive world model built from a single traversal of the environment, a pre-trained visual feature encoder, and stochastic environmental augmentation, to demonstrate successful zero-shot transfer under real-world environmental variations without fine-tuning.
Tasks	Robot Navigation
Published	2017-11-28
URL	http://arxiv.org/abs/1711.10137v2
PDF	http://arxiv.org/pdf/1711.10137v2.pdf
PWC	https://paperswithcode.com/paper/one-shot-reinforcement-learning-for-robot
Repo	https://github.com/ayusefi/Localization-Papers
Framework	none

The Code2Text Challenge: Text Generation in Source Code Libraries


Title	The Code2Text Challenge: Text Generation in Source Code Libraries
Authors	Kyle Richardson, Sina Zarrieß, Jonas Kuhn
Abstract	We propose a new shared task for tactical data-to-text generation in the domain of source code libraries. Specifically, we focus on text generation of function descriptions from example software projects. Data is drawn from existing resources used for studying the related problem of semantic parser induction (Richardson and Kuhn, 2017b; Richardson and Kuhn, 2017a), and spans a wide variety of both natural languages and programming languages. In this paper, we describe these existing resources, which will serve as training and development data for the task, and discuss plans for building new independent test sets.
Tasks	Data-to-Text Generation, Text Generation
Published	2017-07-31
URL	http://arxiv.org/abs/1708.00098v1
PDF	http://arxiv.org/pdf/1708.00098v1.pdf
PWC	https://paperswithcode.com/paper/the-code2text-challenge-text-generation-in
Repo	https://github.com/yakazimir/Code-Datasets
Framework	none

Multi-Scale Dense Networks for Resource Efficient Image Classification


Title	Multi-Scale Dense Networks for Resource Efficient Image Classification
Authors	Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Q. Weinberger
Abstract	In this paper we investigate image classification with computational resource limits at test time. Two such settings are: 1. anytime classification, where the network’s prediction for a test example is progressively updated, facilitating the output of a prediction at any time; and 2. budgeted batch classification, where a fixed amount of computation is available to classify a set of examples that can be spent unevenly across “easier” and “harder” inputs. In contrast to most prior work, such as the popular Viola and Jones algorithm, our approach is based on convolutional neural networks. We train multiple classifiers with varying resource demands, which we adaptively apply during test time. To maximally re-use computation between the classifiers, we incorporate them as early-exits into a single deep convolutional neural network and inter-connect them with dense connectivity. To facilitate high quality classification early on, we use a two-dimensional multi-scale network architecture that maintains coarse and fine level features all-throughout the network. Experiments on three image-classification tasks demonstrate that our framework substantially improves the existing state-of-the-art in both settings.
Tasks	Image Classification
Published	2017-03-29
URL	http://arxiv.org/abs/1703.09844v5
PDF	http://arxiv.org/pdf/1703.09844v5.pdf
PWC	https://paperswithcode.com/paper/multi-scale-dense-networks-for-resource
Repo	https://github.com/gaohuang/MSDNet
Framework	pytorch

LEPOR: An Augmented Machine Translation Evaluation Metric


Title	LEPOR: An Augmented Machine Translation Evaluation Metric
Authors	Aaron Li-Feng Han
Abstract	Machine translation (MT) was developed as one of the hottest research topics in the natural language processing (NLP) literature. One important issue in MT is that how to evaluate the MT system reasonably and tell us whether the translation system makes an improvement or not. The traditional manual judgment methods are expensive, time-consuming, unrepeatable, and sometimes with low agreement. On the other hand, the popular automatic MT evaluation methods have some weaknesses. Firstly, they tend to perform well on the language pairs with English as the target language, but weak when English is used as source. Secondly, some methods rely on many additional linguistic features to achieve good performance, which makes the metric unable to replicate and apply to other language pairs easily. Thirdly, some popular metrics utilize incomprehensive factors, which result in low performance on some practical tasks. In this thesis, to address the existing problems, we design novel MT evaluation methods and investigate their performances on different languages. Firstly, we design augmented factors to yield highly accurate evaluation.Secondly, we design a tunable evaluation model where weighting of factors can be optimised according to the characteristics of languages. Thirdly, in the enhanced version of our methods, we design concise linguistic feature using POS to show that our methods can yield even higher performance when using some external linguistic resources. Finally, we introduce the practical performance of our metrics in the ACL-WMT workshop shared tasks, which show that the proposed methods are robust across different languages.
Tasks	Machine Translation
Published	2017-03-26
URL	http://arxiv.org/abs/1703.08748v1
PDF	http://arxiv.org/pdf/1703.08748v1.pdf
PWC	https://paperswithcode.com/paper/lepor-an-augmented-machine-translation
Repo	https://github.com/poethan/LEPOR
Framework	none

Safety-Aware Apprenticeship Learning


Title	Safety-Aware Apprenticeship Learning
Authors	Weichao Zhou, Wenchao Li
Abstract	Apprenticeship learning (AL) is a kind of Learning from Demonstration techniques where the reward function of a Markov Decision Process (MDP) is unknown to the learning agent and the agent has to derive a good policy by observing an expert’s demonstrations. In this paper, we study the problem of how to make AL algorithms inherently safe while still meeting its learning objective. We consider a setting where the unknown reward function is assumed to be a linear combination of a set of state features, and the safety property is specified in Probabilistic Computation Tree Logic (PCTL). By embedding probabilistic model checking inside AL, we propose a novel counterexample-guided approach that can ensure safety while retaining performance of the learnt policy. We demonstrate the effectiveness of our approach on several challenging AL scenarios where safety is essential.
Tasks
Published	2017-10-22
URL	http://arxiv.org/abs/1710.07983v4
PDF	http://arxiv.org/pdf/1710.07983v4.pdf
PWC	https://paperswithcode.com/paper/safety-aware-apprenticeship-learning
Repo	https://github.com/zwc662/CAV2018
Framework	none

LIUM Machine Translation Systems for WMT17 News Translation Task


Title	LIUM Machine Translation Systems for WMT17 News Translation Task
Authors	Mercedes García-Martínez, Ozan Caglayan, Walid Aransa, Adrien Bardet, Fethi Bougares, Loïc Barrault
Abstract	This paper describes LIUM submissions to WMT17 News Translation Task for English-German, English-Turkish, English-Czech and English-Latvian language pairs. We train BPE-based attentive Neural Machine Translation systems with and without factored outputs using the open source nmtpy framework. Competitive scores were obtained by ensembling various systems and exploiting the availability of target monolingual corpora for back-translation. The impact of back-translation quantity and quality is also analyzed for English-Turkish where our post-deadline submission surpassed the best entry by +1.6 BLEU.
Tasks	Machine Translation
Published	2017-07-14
URL	http://arxiv.org/abs/1707.04499v1
PDF	http://arxiv.org/pdf/1707.04499v1.pdf
PWC	https://paperswithcode.com/paper/lium-machine-translation-systems-for-wmt17
Repo	https://github.com/lium-lst/wmt17-newstask
Framework	none


Title	Sharing deep generative representation for perceived image reconstruction from human brain activity
Authors	Changde Du, Changying Du, Huiguang He
Abstract	Decoding human brain activities via functional magnetic resonance imaging (fMRI) has gained increasing attention in recent years. While encouraging results have been reported in brain states classification tasks, reconstructing the details of human visual experience still remains difficult. Two main challenges that hinder the development of effective models are the perplexing fMRI measurement noise and the high dimensionality of limited data instances. Existing methods generally suffer from one or both of these issues and yield dissatisfactory results. In this paper, we tackle this problem by casting the reconstruction of visual stimulus as the Bayesian inference of missing view in a multiview latent variable model. Sharing a common latent representation, our joint generative model of external stimulus and brain response is not only “deep” in extracting nonlinear features from visual images, but also powerful in capturing correlations among voxel activities of fMRI recordings. The nonlinearity and deep structure endow our model with strong representation ability, while the correlations of voxel activities are critical for suppressing noise and improving prediction. We devise an efficient variational Bayesian method to infer the latent variables and the model parameters. To further improve the reconstruction accuracy, the latent representations of testing instances are enforced to be close to that of their neighbours from the training set via posterior regularization. Experiments on three fMRI recording datasets demonstrate that our approach can more accurately reconstruct visual stimuli.
Tasks	Bayesian Inference, Image Reconstruction
Published	2017-04-25
URL	http://arxiv.org/abs/1704.07575v3
PDF	http://arxiv.org/pdf/1704.07575v3.pdf
PWC	https://paperswithcode.com/paper/sharing-deep-generative-representation-for
Repo	https://github.com/ChangdeDu/DGMM
Framework	none

Unsupervised Learning by Predicting Noise


Title	Unsupervised Learning by Predicting Noise
Authors	Piotr Bojanowski, Armand Joulin
Abstract	Convolutional neural networks provide visual features that perform remarkably well in many computer vision applications. However, training these networks requires significant amounts of supervision. This paper introduces a generic framework to train deep networks, end-to-end, with no supervision. We propose to fix a set of target representations, called Noise As Targets (NAT), and to constrain the deep features to align to them. This domain agnostic approach avoids the standard unsupervised learning issues of trivial solutions and collapsing of features. Thanks to a stochastic batch reassignment strategy and a separable square loss function, it scales to millions of images. The proposed approach produces representations that perform on par with state-of-the-art unsupervised methods on ImageNet and Pascal VOC.
Tasks
Published	2017-04-18
URL	http://arxiv.org/abs/1704.05310v1
PDF	http://arxiv.org/pdf/1704.05310v1.pdf
PWC	https://paperswithcode.com/paper/unsupervised-learning-by-predicting-noise
Repo	https://github.com/facebookresearch/noise-as-targets
Framework	torch

A Generalization of Convolutional Neural Networks to Graph-Structured Data


Title	A Generalization of Convolutional Neural Networks to Graph-Structured Data
Authors	Yotam Hechtlinger, Purvasha Chakravarti, Jining Qin
Abstract	This paper introduces a generalization of Convolutional Neural Networks (CNNs) from low-dimensional grid data, such as images, to graph-structured data. We propose a novel spatial convolution utilizing a random walk to uncover the relations within the input, analogous to the way the standard convolution uses the spatial neighborhood of a pixel on the grid. The convolution has an intuitive interpretation, is efficient and scalable and can also be used on data with varying graph structure. Furthermore, this generalization can be applied to many standard regression or classification problems, by learning the the underlying graph. We empirically demonstrate the performance of the proposed CNN on MNIST, and challenge the state-of-the-art on Merck molecular activity data set.
Tasks
Published	2017-04-26
URL	http://arxiv.org/abs/1704.08165v1
PDF	http://arxiv.org/pdf/1704.08165v1.pdf
PWC	https://paperswithcode.com/paper/a-generalization-of-convolutional-neural
Repo	https://github.com/hechtlinger/graph_cnn
Framework	none

Image reconstruction by domain transform manifold learning


Title	Image reconstruction by domain transform manifold learning
Authors	Bo Zhu, Jeremiah Z. Liu, Bruce R. Rosen, Matthew S. Rosen
Abstract	Image reconstruction plays a critical role in the implementation of all contemporary imaging modalities across the physical and life sciences including optical, MRI, CT, PET, and radio astronomy. During an image acquisition, the sensor encodes an intermediate representation of an object in the sensor domain, which is subsequently reconstructed into an image by an inversion of the encoding function. Image reconstruction is challenging because analytic knowledge of the inverse transform may not exist a priori, especially in the presence of sensor non-idealities and noise. Thus, the standard reconstruction approach involves approximating the inverse function with multiple ad hoc stages in a signal processing chain whose composition depends on the details of each acquisition strategy, and often requires expert parameter tuning to optimize reconstruction performance. We present here a unified framework for image reconstruction, AUtomated TransfOrm by Manifold APproximation (AUTOMAP), which recasts image reconstruction as a data-driven, supervised learning task that allows a mapping between sensor and image domain to emerge from an appropriate corpus of training data. We implement AUTOMAP with a deep neural network and exhibit its flexibility in learning reconstruction transforms for a variety of MRI acquisition strategies, using the same network architecture and hyperparameters. We further demonstrate its efficiency in sparsely representing transforms along low-dimensional manifolds, resulting in superior immunity to noise and reconstruction artifacts compared with conventional handcrafted reconstruction methods. In addition to improving the reconstruction performance of existing acquisition methodologies, we anticipate accelerating the discovery of new acquisition strategies across modalities as the burden of reconstruction becomes lifted by AUTOMAP and learned-reconstruction approaches.
Tasks	Image Reconstruction
Published	2017-04-28
URL	http://arxiv.org/abs/1704.08841v1
PDF	http://arxiv.org/pdf/1704.08841v1.pdf
PWC	https://paperswithcode.com/paper/image-reconstruction-by-domain-transform
Repo	https://github.com/chongduan/MRI-AUTOMAP
Framework	tf

Selective Encoding for Abstractive Sentence Summarization


Title	Selective Encoding for Abstractive Sentence Summarization
Authors	Qingyu Zhou, Nan Yang, Furu Wei, Ming Zhou
Abstract	We propose a selective encoding model to extend the sequence-to-sequence framework for abstractive sentence summarization. It consists of a sentence encoder, a selective gate network, and an attention equipped decoder. The sentence encoder and decoder are built with recurrent neural networks. The selective gate network constructs a second level sentence representation by controlling the information flow from encoder to decoder. The second level representation is tailored for sentence summarization task, which leads to better performance. We evaluate our model on the English Gigaword, DUC 2004 and MSR abstractive sentence summarization datasets. The experimental results show that the proposed selective encoding model outperforms the state-of-the-art baseline models.
Tasks	Abstractive Sentence Summarization
Published	2017-04-24
URL	http://arxiv.org/abs/1704.07073v1
PDF	http://arxiv.org/pdf/1704.07073v1.pdf
PWC	https://paperswithcode.com/paper/selective-encoding-for-abstractive-sentence
Repo	https://github.com/toru34/zhou_acl_2017
Framework	none

A Tutorial on Deep Learning for Music Information Retrieval


Title	A Tutorial on Deep Learning for Music Information Retrieval
Authors	Keunwoo Choi, György Fazekas, Kyunghyun Cho, Mark Sandler
Abstract	Following their success in Computer Vision and other areas, deep learning techniques have recently become widely adopted in Music Information Retrieval (MIR) research. However, the majority of works aim to adopt and assess methods that have been shown to be effective in other domains, while there is still a great need for more original research focusing on music primarily and utilising musical knowledge and insight. The goal of this paper is to boost the interest of beginners by providing a comprehensive tutorial and reducing the barriers to entry into deep learning for MIR. We lay out the basic principles and review prominent works in this hard to navigate the field. We then outline the network structures that have been successful in MIR problems and facilitate the selection of building blocks for the problems at hand. Finally, guidelines for new tasks and some advanced topics in deep learning are discussed to stimulate new research in this fascinating field.
Tasks	Information Retrieval, Music Information Retrieval
Published	2017-09-13
URL	http://arxiv.org/abs/1709.04396v2
PDF	http://arxiv.org/pdf/1709.04396v2.pdf
PWC	https://paperswithcode.com/paper/a-tutorial-on-deep-learning-for-music
Repo	https://github.com/keunwoochoi/dl4mir
Framework	none