October 18, 2019

2703 words 13 mins read

Paper Group ANR 561

Paper Group ANR 561

Some Approximation Bounds for Deep Networks. Online Bandit Linear Optimization: A Study. Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images. From Hashing to CNNs: Training BinaryWeight Networks via Hashing. Generating new pictures in complex datasets with a simple neural network. The RGNLP Machine Transla …

Some Approximation Bounds for Deep Networks

Title Some Approximation Bounds for Deep Networks
Authors Brendan McCane, Lech Szymanski
Abstract In this paper we introduce new bounds on the approximation of functions in deep networks and in doing so introduce some new deep network architectures for function approximation. These results give some theoretical insight into the success of autoencoders and ResNets.
Tasks
Published 2018-03-08
URL http://arxiv.org/abs/1803.02956v1
PDF http://arxiv.org/pdf/1803.02956v1.pdf
PWC https://paperswithcode.com/paper/some-approximation-bounds-for-deep-networks
Repo
Framework

Online Bandit Linear Optimization: A Study

Title Online Bandit Linear Optimization: A Study
Authors Vikram Mullachery, Samarth Tiwari
Abstract This article introduces the concepts around Online Bandit Linear Optimization and explores an efficient setup called SCRiBLe (Self-Concordant Regularization in Bandit Learning) created by Abernethy et. al.\cite{abernethy}. The SCRiBLe setup and algorithm yield a $O(\sqrt{T})$ regret bound and polynomial run time complexity bound on the dimension of the input space. In this article we build up to the bandit linear optimization case and study SCRiBLe.
Tasks
Published 2018-05-11
URL http://arxiv.org/abs/1805.05773v1
PDF http://arxiv.org/pdf/1805.05773v1.pdf
PWC https://paperswithcode.com/paper/online-bandit-linear-optimization-a-study
Repo
Framework

Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images

Title Adversarial Domain Adaptation for Classification of Prostate Histopathology Whole-Slide Images
Authors Jian Ren, Ilker Hacihaliloglu, Eric A. Singer, David J. Foran, Xin Qi
Abstract Automatic and accurate Gleason grading of histopathology tissue slides is crucial for prostate cancer diagnosis, treatment, and prognosis. Usually, histopathology tissue slides from different institutions show heterogeneous appearances because of different tissue preparation and staining procedures, thus the predictable model learned from one domain may not be applicable to a new domain directly. Here we propose to adopt unsupervised domain adaptation to transfer the discriminative knowledge obtained from the source domain to the target domain without requiring labeling of images at the target domain. The adaptation is achieved through adversarial training to find an invariant feature space along with the proposed Siamese architecture on the target domain to add a regularization that is appropriate for the whole-slide images. We validate the method on two prostate cancer datasets and obtain significant classification improvement of Gleason scores as compared with the baseline models.
Tasks Domain Adaptation, Unsupervised Domain Adaptation
Published 2018-06-04
URL http://arxiv.org/abs/1806.01357v2
PDF http://arxiv.org/pdf/1806.01357v2.pdf
PWC https://paperswithcode.com/paper/adversarial-domain-adaptation-for
Repo
Framework

From Hashing to CNNs: Training BinaryWeight Networks via Hashing

Title From Hashing to CNNs: Training BinaryWeight Networks via Hashing
Authors Qinghao Hu, Peisong Wang, Jian Cheng
Abstract Deep convolutional neural networks (CNNs) have shown appealing performance on various computer vision tasks in recent years. This motivates people to deploy CNNs to realworld applications. However, most of state-of-art CNNs require large memory and computational resources, which hinders the deployment on mobile devices. Recent studies show that low-bit weight representation can reduce much storage and memory demand, and also can achieve efficient network inference. To achieve this goal, we propose a novel approach named BWNH to train Binary Weight Networks via Hashing. In this paper, we first reveal the strong connection between inner-product preserving hashing and binary weight networks, and show that training binary weight networks can be intrinsically regarded as a hashing problem. Based on this perspective, we propose an alternating optimization method to learn the hash codes instead of directly learning binary weights. Extensive experiments on CIFAR10, CIFAR100 and ImageNet demonstrate that our proposed BWNH outperforms current state-of-art by a large margin.
Tasks
Published 2018-02-08
URL http://arxiv.org/abs/1802.02733v1
PDF http://arxiv.org/pdf/1802.02733v1.pdf
PWC https://paperswithcode.com/paper/from-hashing-to-cnns-training-binaryweight
Repo
Framework

Generating new pictures in complex datasets with a simple neural network

Title Generating new pictures in complex datasets with a simple neural network
Authors Galin Georgiev
Abstract We introduce a version of a variational auto-encoder (VAE), which can generate good perturbations of images, when trained on a complex dataset (in our experiments, CIFAR-10). The net is using only two latent generative dimensions per class, with uni-modal probability density. The price one has to pay for good generation is that not all training images are well reconstructed. An additional classifier is required to determine which training image is well reconstructed and generally the weights of training images. Only training images which are well reconstructed, can be perturbed. For good perturbations, we use the tentative empirical drifts of well reconstructed images. The construct is not predictive in the usual statistical sense.
Tasks
Published 2018-10-30
URL https://arxiv.org/abs/1810.12478v3
PDF https://arxiv.org/pdf/1810.12478v3.pdf
PWC https://paperswithcode.com/paper/generating-new-pictures-in-complex-datasets
Repo
Framework

The RGNLP Machine Translation Systems for WAT 2018

Title The RGNLP Machine Translation Systems for WAT 2018
Authors Atul Kr. Ojha, Koel Dutta Chowdhury, Chao-Hong Liu, Karan Saxena
Abstract This paper presents the system description of Machine Translation (MT) system(s) for Indic Languages Multilingual Task for the 2018 edition of the WAT Shared Task. In our experiments, we (the RGNLP team) explore both statistical and neural methods across all language pairs. (We further present an extensive comparison of language-related problems for both the approaches in the context of low-resourced settings.) Our PBSMT models were highest score on all automatic evaluation metrics in the English into Telugu, Hindi, Bengali, Tamil portion of the shared task.
Tasks Machine Translation
Published 2018-12-03
URL http://arxiv.org/abs/1812.00798v1
PDF http://arxiv.org/pdf/1812.00798v1.pdf
PWC https://paperswithcode.com/paper/the-rgnlp-machine-translation-systems-for-wat
Repo
Framework

Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial Networks

Title Stochastic Deconvolutional Neural Network Ensemble Training on Generative Pseudo-Adversarial Networks
Authors Alexey Chaplygin, Joshua Chacksfield
Abstract The training of Generative Adversarial Networks is a difficult task mainly due to the nature of the networks. One such issue is when the generator and discriminator start oscillating, rather than converging to a fixed point. Another case can be when one agent becomes more adept than the other which results in the decrease of the other agent’s ability to learn, reducing the learning capacity of the system as a whole. Additionally, there exists the problem of Mode Collapse which involves the generators output collapsing to a single sample or a small set of similar samples. To train GANs a careful selection of the architecture that is used along with a variety of other methods to improve training. Even when applying these methods there is low stability of training in relation to the parameters that are chosen. Stochastic ensembling is suggested as a method for improving the stability while training GANs.
Tasks
Published 2018-02-07
URL http://arxiv.org/abs/1802.02436v1
PDF http://arxiv.org/pdf/1802.02436v1.pdf
PWC https://paperswithcode.com/paper/stochastic-deconvolutional-neural-network
Repo
Framework

Sketching for Principal Component Regression

Title Sketching for Principal Component Regression
Authors Liron Mor-Yosef, Haim Avron
Abstract Principal component regression (PCR) is a useful method for regularizing linear regression. Although conceptually simple, straightforward implementations of PCR have high computational costs and so are inappropriate when learning with large scale data. In this paper, we propose efficient algorithms for computing approximate PCR solutions that are, on one hand, high quality approximations to the true PCR solutions (when viewed as minimizer of a constrained optimization problem), and on the other hand entertain rigorous risk bounds (when viewed as statistical estimators). In particular, we propose an input sparsity time algorithms for approximate PCR. We also consider computing an approximate PCR in the streaming model, and kernel PCR. Empirical results demonstrate the excellent performance of our proposed methods.
Tasks
Published 2018-03-07
URL http://arxiv.org/abs/1803.02661v2
PDF http://arxiv.org/pdf/1803.02661v2.pdf
PWC https://paperswithcode.com/paper/sketching-for-principal-component-regression
Repo
Framework

Connecting Distant Entities with Induction through Conditional Random Fields for Named Entity Recognition: Precursor-Induced CRF

Title Connecting Distant Entities with Induction through Conditional Random Fields for Named Entity Recognition: Precursor-Induced CRF
Authors Wangjin Lee, Jinwook Choi
Abstract This paper presents a method of designing specific high-order dependency factor on the linear chain conditional random fields (CRFs) for named entity recognition (NER). Named entities tend to be separated from each other by multiple outside tokens in a text, and thus the first-order CRF, as well as the second-order CRF, may innately lose transition information between distant named entities. The proposed design uses outside label in NER as a transmission medium of precedent entity information on the CRF. Then, empirical results apparently demonstrate that it is possible to exploit long-distance label dependency in the original first-order linear chain CRF structure upon NER while reducing computational loss rather than in the second-order CRF.
Tasks Named Entity Recognition
Published 2018-05-26
URL http://arxiv.org/abs/1805.10414v1
PDF http://arxiv.org/pdf/1805.10414v1.pdf
PWC https://paperswithcode.com/paper/connecting-distant-entities-with-induction
Repo
Framework

Robust Continuous Co-Clustering

Title Robust Continuous Co-Clustering
Authors Xiao He, Luis Moreira-Matias
Abstract Clustering consists of grouping together samples giving their similar properties. The problem of modeling simultaneously groups of samples and features is known as Co-Clustering. This paper introduces ROCCO - a Robust Continuous Co-Clustering algorithm. ROCCO is a scalable, hyperparameter-free, easy and ready to use algorithm to address Co-Clustering problems in practice over massive cross-domain datasets. It operates by learning a graph-based two-sided representation of the input matrix. The underlying proposed optimization problem is non-convex, which assures a flexible pool of solutions. Moreover, we prove that it can be solved with a near linear time complexity on the input size. An exhaustive large-scale experimental testbed conducted with both synthetic and real-world datasets demonstrates ROCCO’s properties in practice: (i) State-of-the-art performance in cross-domain real-world problems including Biomedicine and Text Mining; (ii) very low sensitivity to hyperparameter settings; (iii) robustness to noise and (iv) a linear empirical scalability in practice. These results highlight ROCCO as a powerful general-purpose co-clustering algorithm for cross-domain practitioners, regardless of their technical background.
Tasks
Published 2018-02-14
URL http://arxiv.org/abs/1802.05036v1
PDF http://arxiv.org/pdf/1802.05036v1.pdf
PWC https://paperswithcode.com/paper/robust-continuous-co-clustering
Repo
Framework

Addendum to “HTN Acting: A Formalism and an Algorithm”

Title Addendum to “HTN Acting: A Formalism and an Algorithm”
Authors Lavindra de Silva
Abstract Hierarchical Task Network (HTN) planning is a practical and efficient approach to planning when the ‘standard operating procedures’ for a domain are available. Like Belief-Desire-Intention (BDI) agent reasoning, HTN planning performs hierarchical and context-based refinement of goals into subgoals and basic actions. However, while HTN planners ‘lookahead’ over the consequences of choosing one refinement over another, BDI agents interleave refinement with acting. There has been renewed interest in making HTN planners behave more like BDI agent systems, e.g. to have a unified representation for acting and planning. However, past work on the subject has remained informal or implementation-focused. This paper is a formal account of ‘HTN acting’, which supports interleaved deliberation, acting, and failure recovery. We use the syntax of the most general HTN planning formalism and build on its core semantics, and we provide an algorithm which combines our new formalism with the processing of exogenous events. We also study the properties of HTN acting and its relation to HTN planning.
Tasks
Published 2018-06-06
URL http://arxiv.org/abs/1806.02127v1
PDF http://arxiv.org/pdf/1806.02127v1.pdf
PWC https://paperswithcode.com/paper/addendum-to-htn-acting-a-formalism-and-an
Repo
Framework

DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)

Title DA-GAN: Instance-level Image Translation by Deep Attention Generative Adversarial Networks (with Supplementary Materials)
Authors Shuang Ma, Jianlong Fu, Chang Wen Chen, Tao Mei
Abstract Unsupervised image translation, which aims in translating two independent sets of images, is challenging in discovering the correct correspondences without paired data. Existing works build upon Generative Adversarial Network (GAN) such that the distribution of the translated images are indistinguishable from the distribution of the target set. However, such set-level constraints cannot learn the instance-level correspondences (e.g. aligned semantic parts in object configuration task). This limitation often results in false positives (e.g. geometric or semantic artifacts), and further leads to mode collapse problem. To address the above issues, we propose a novel framework for instance-level image translation by Deep Attention GAN (DA-GAN). Such a design enables DA-GAN to decompose the task of translating samples from two sets into translating instances in a highly-structured latent space. Specifically, we jointly learn a deep attention encoder, and the instancelevel correspondences could be consequently discovered through attending on the learned instance pairs. Therefore, the constraints could be exploited on both set-level and instance-level. Comparisons against several state-ofthe- arts demonstrate the superiority of our approach, and the broad application capability, e.g, pose morphing, data augmentation, etc., pushes the margin of domain translation problem.
Tasks Data Augmentation, Deep Attention
Published 2018-02-18
URL http://arxiv.org/abs/1802.06454v1
PDF http://arxiv.org/pdf/1802.06454v1.pdf
PWC https://paperswithcode.com/paper/da-gan-instance-level-image-translation-by
Repo
Framework

Mapping, Localization and Path Planning for Image-based Navigation using Visual Features and Map

Title Mapping, Localization and Path Planning for Image-based Navigation using Visual Features and Map
Authors Janine Thoma, Danda Pani Paudel, Ajad Chhatkuli, Thomas Probst, Luc Van Gool
Abstract Building on progress in feature representations for image retrieval, image-based localization has seen a surge of research interest. Image-based localization has the advantage of being inexpensive and efficient, often avoiding the use of 3D metric maps altogether. That said, the need to maintain a large number of reference images as an effective support of localization in a scene, nonetheless calls for them to be organized in a map structure of some kind. The problem of localization often arises as part of a navigation process. We are, therefore, interested in summarizing the reference images as a set of landmarks, which meet the requirements for image-based navigation. A contribution of this paper is to formulate such a set of requirements for the two sub-tasks involved: map construction and self-localization. These requirements are then exploited for compact map representation and accurate self-localization, using the framework of a network flow problem. During this process, we formulate the map construction and self-localization problems as convex quadratic and second-order cone programs, respectively. We evaluate our methods on publicly available indoor and outdoor datasets, where they outperform existing methods significantly.
Tasks Image-Based Localization, Image Retrieval
Published 2018-12-10
URL https://arxiv.org/abs/1812.03795v2
PDF https://arxiv.org/pdf/1812.03795v2.pdf
PWC https://paperswithcode.com/paper/image-based-navigation-using-visual-features
Repo
Framework

Boosting up Scene Text Detectors with Guided CNN

Title Boosting up Scene Text Detectors with Guided CNN
Authors Xiaoyu Yue, Zhanghui Kuang, Zhaoyang Zhang, Zhenfang Chen, Pan He, Yu Qiao, Wei Zhang
Abstract Deep CNNs have achieved great success in text detection. Most of existing methods attempt to improve accuracy with sophisticated network design, while paying less attention on speed. In this paper, we propose a general framework for text detection called Guided CNN to achieve the two goals simultaneously. The proposed model consists of one guidance subnetwork, where a guidance mask is learned from the input image itself, and one primary text detector, where every convolution and non-linear operation are conducted only in the guidance mask. On the one hand, the guidance subnetwork filters out non-text regions coarsely, greatly reduces the computation complexity. On the other hand, the primary text detector focuses on distinguishing between text and hard non-text regions and regressing text bounding boxes, achieves a better detection accuracy. A training strategy, called background-aware block-wise random synthesis, is proposed to further boost up the performance. We demonstrate that the proposed Guided CNN is not only effective but also efficient with two state-of-the-art methods, CTPN and EAST, as backbones. On the challenging benchmark ICDAR 2013, it speeds up CTPN by 2.9 times on average, while improving the F-measure by 1.5%. On ICDAR 2015, it speeds up EAST by 2.0 times while improving the F-measure by 1.0%.
Tasks
Published 2018-05-10
URL http://arxiv.org/abs/1805.04132v2
PDF http://arxiv.org/pdf/1805.04132v2.pdf
PWC https://paperswithcode.com/paper/boosting-up-scene-text-detectors-with-guided
Repo
Framework

Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation

Title Simultaneously Optimizing Weight and Quantizer of Ternary Neural Network using Truncated Gaussian Approximation
Authors Zhezhi He, Deliang Fan
Abstract In the past years, Deep convolution neural network has achieved great success in many artificial intelligence applications. However, its enormous model size and massive computation cost have become the main obstacle for deployment of such powerful algorithm in the low power and resource-limited mobile systems. As the countermeasure to this problem, deep neural networks with ternarized weights (i.e. -1, 0, +1) have been widely explored to greatly reduce the model size and computational cost, with limited accuracy degradation. In this work, we propose a novel ternarized neural network training method which simultaneously optimizes both weights and quantizer during training, differentiating from prior works. Instead of fixed and uniform weight ternarization, we are the first to incorporate the thresholds of weight ternarization into a closed-form representation using the truncated Gaussian approximation, enabling simultaneous optimization of weights and quantizer through back-propagation training. With both of the first and last layer ternarized, the experiments on the ImageNet classification task show that our ternarized ResNet-18/34/50 only has 3.9/2.52/2.16% accuracy degradation in comparison to the full-precision counterparts.
Tasks
Published 2018-10-02
URL http://arxiv.org/abs/1810.01018v1
PDF http://arxiv.org/pdf/1810.01018v1.pdf
PWC https://paperswithcode.com/paper/simultaneously-optimizing-weight-and
Repo
Framework
comments powered by Disqus