July 27, 2019

2566 words 13 mins read

Paper Group ANR 740

Content-Based Image Retrieval Based on Late Fusion of Binary and Local Descriptors. On overfitting and asymptotic bias in batch reinforcement learning with partial observability. Development of JavaScript-based deep learning platform and application to distributed training. Meta-Learning for Resampling Recommendation Systems. Analysing Soccer Games …

Content-Based Image Retrieval Based on Late Fusion of Binary and Local Descriptors


Title	Content-Based Image Retrieval Based on Late Fusion of Binary and Local Descriptors
Authors	Nouman Ali, Danish Ali Mazhar, Zeshan Iqbal, Rehan Ashraf, Jawad Ahmed, Farrukh Zeeshan Khan
Abstract	One of the challenges in Content-Based Image Retrieval (CBIR) is to reduce the semantic gaps between low-level features and high-level semantic concepts. In CBIR, the images are represented in the feature space and the performance of CBIR depends on the type of selected feature representation. Late fusion also known as visual words integration is applied to enhance the performance of image retrieval. The recent advances in image retrieval diverted the focus of research towards the use of binary descriptors as they are reported computationally efficient. In this paper, we aim to investigate the late fusion of Fast Retina Keypoint (FREAK) and Scale Invariant Feature Transform (SIFT). The late fusion of binary and local descriptor is selected because among binary descriptors, FREAK has shown good results in classification-based problems while SIFT is robust to translation, scaling, rotation and small distortions. The late fusion of FREAK and SIFT integrates the performance of both feature descriptors for an effective image retrieval. Experimental results and comparisons show that the proposed late fusion enhances the performances of image retrieval.
Tasks	Content-Based Image Retrieval, Image Retrieval
Published	2017-03-24
URL	http://arxiv.org/abs/1703.08492v1
PDF	http://arxiv.org/pdf/1703.08492v1.pdf
PWC	https://paperswithcode.com/paper/content-based-image-retrieval-based-on-late
Repo
Framework

On overfitting and asymptotic bias in batch reinforcement learning with partial observability


Title	On overfitting and asymptotic bias in batch reinforcement learning with partial observability
Authors	Vincent Francois-Lavet, Guillaume Rabusseau, Joelle Pineau, Damien Ernst, Raphael Fonteneau
Abstract	This paper provides an analysis of the tradeoff between asymptotic bias (suboptimality with unlimited data) and overfitting (additional suboptimality due to limited data) in the context of reinforcement learning with partial observability. Our theoretical analysis formally characterizes that while potentially increasing the asymptotic bias, a smaller state representation decreases the risk of overfitting. This analysis relies on expressing the quality of a state representation by bounding L1 error terms of the associated belief states. Theoretical results are empirically illustrated when the state representation is a truncated history of observations, both on synthetic POMDPs and on a large-scale POMDP in the context of smartgrids, with real-world data. Finally, similarly to known results in the fully observable setting, we also briefly discuss and empirically illustrate how using function approximators and adapting the discount factor may enhance the tradeoff between asymptotic bias and overfitting in the partially observable context.
Tasks
Published	2017-09-22
URL	http://arxiv.org/abs/1709.07796v2
PDF	http://arxiv.org/pdf/1709.07796v2.pdf
PWC	https://paperswithcode.com/paper/on-overfitting-and-asymptotic-bias-in-batch
Repo
Framework

Development of JavaScript-based deep learning platform and application to distributed training


Title	Development of JavaScript-based deep learning platform and application to distributed training
Authors	Masatoshi Hidaka, Ken Miura, Tatsuya Harada
Abstract	Deep learning is increasingly attracting attention for processing big data. Existing frameworks for deep learning must be set up to specialized computer systems. Gaining sufficient computing resources therefore entails high costs of deployment and maintenance. In this work, we implement a matrix library and deep learning framework that uses JavaScript. It can run on web browsers operating on ordinary personal computers and smartphones. Using JavaScript, deep learning can be accomplished in widely diverse environments without the necessity for software installation. Using GPGPU from WebCL framework, our framework can train large scale convolutional neural networks such as VGGNet and ResNet. In the experiments, we demonstrate their practicality by training VGGNet in a distributed manner using web browsers as the client.
Tasks
Published	2017-02-07
URL	http://arxiv.org/abs/1702.01846v3
PDF	http://arxiv.org/pdf/1702.01846v3.pdf
PWC	https://paperswithcode.com/paper/development-of-javascript-based-deep-learning
Repo
Framework

Meta-Learning for Resampling Recommendation Systems


Title	Meta-Learning for Resampling Recommendation Systems
Authors	Smolyakov Dmitry, Alexander Korotin, Pavel Erofeev, Artem Papanov, Evgeny Burnaev
Abstract	One possible approach to tackle the class imbalance in classification tasks is to resample a training dataset, i.e., to drop some of its elements or to synthesize new ones. There exist several widely-used resampling methods. Recent research showed that the choice of resampling method significantly affects the quality of classification, which raises resampling selection problem. Exhaustive search for optimal resampling is time-consuming and hence it is of limited use. In this paper, we describe an alternative approach to the resampling selection. We follow the meta-learning concept to build resampling recommendation systems, i.e., algorithms recommending resampling for datasets on the basis of their properties.
Tasks	Meta-Learning, Recommendation Systems
Published	2017-06-06
URL	http://arxiv.org/abs/1706.02289v4
PDF	http://arxiv.org/pdf/1706.02289v4.pdf
PWC	https://paperswithcode.com/paper/meta-learning-for-resampling-recommendation
Repo
Framework

Analysing Soccer Games with Clustering and Conceptors


Title	Analysing Soccer Games with Clustering and Conceptors
Authors	Olivia Michael, Oliver Obst, Falk Schmidsberger, Frieder Stolzenburg
Abstract	We present a new approach for identifying situations and behaviours, which we call “moves”, from soccer games in the 2D simulation league. Being able to identify key situations and behaviours are useful capabilities for analysing soccer matches, anticipating opponent behaviours to aid selection of appropriate tactics, and also as a prerequisite for automatic learning of behaviours and policies. To support a wide set of strategies, our goal is to identify situations from data, in an unsupervised way without making use of pre-defined soccer specific concepts such as “pass” or “dribble”. The recurrent neural networks we use in our approach act as a high-dimensional projection of the recent history of a situation on the field. Similar situations, i.e., with similar histories, are found by clustering of network states. The same networks are also used to learn so-called conceptors, that are lower-dimensional manifolds that describe trajectories through a high-dimensional state space that enable situation-specific predictions from the same neural network. With the proposed approach, we can segment games into sequences of situations that are learnt in an unsupervised way, and learn conceptors that are useful for the prediction of the near future of the respective situation.
Tasks
Published	2017-08-19
URL	http://arxiv.org/abs/1708.05821v1
PDF	http://arxiv.org/pdf/1708.05821v1.pdf
PWC	https://paperswithcode.com/paper/analysing-soccer-games-with-clustering-and
Repo
Framework

Merging $K$-means with hierarchical clustering for identifying general-shaped groups


Title	Merging $K$-means with hierarchical clustering for identifying general-shaped groups
Authors	Anna D. Peterson, Arka P. Ghosh, Ranjan Maitra
Abstract	Clustering partitions a dataset such that observations placed together in a group are similar but different from those in other groups. Hierarchical and $K$-means clustering are two approaches but have different strengths and weaknesses. For instance, hierarchical clustering identifies groups in a tree-like structure but suffers from computational complexity in large datasets while $K$-means clustering is efficient but designed to identify homogeneous spherically-shaped clusters. We present a hybrid non-parametric clustering approach that amalgamates the two methods to identify general-shaped clusters and that can be applied to larger datasets. Specifically, we first partition the dataset into spherical groups using $K$-means. We next merge these groups using hierarchical methods with a data-driven distance measure as a stopping criterion. Our proposal has the potential to reveal groups with general shapes and structure in a dataset. We demonstrate good performance on several simulated and real datasets.
Tasks
Published	2017-12-23
URL	http://arxiv.org/abs/1712.08786v1
PDF	http://arxiv.org/pdf/1712.08786v1.pdf
PWC	https://paperswithcode.com/paper/merging-k-means-with-hierarchical-clustering
Repo
Framework

Semantic Video CNNs through Representation Warping


Title	Semantic Video CNNs through Representation Warping
Authors	Raghudeep Gadde, Varun Jampani, Peter V. Gehler
Abstract	In this work, we propose a technique to convert CNN models for semantic segmentation of static images into CNNs for video data. We describe a warping method that can be used to augment existing architectures with very little extra computational cost. This module is called NetWarp and we demonstrate its use for a range of network architectures. The main design principle is to use optical flow of adjacent frames for warping internal network representations across time. A key insight of this work is that fast optical flow methods can be combined with many different CNN architectures for improved performance and end-to-end training. Experiments validate that the proposed approach incurs only little extra computational cost, while improving performance, when video streams are available. We achieve new state-of-the-art results on the CamVid and Cityscapes benchmark datasets and show consistent improvements over different baseline networks. Our code and models will be available at http://segmentation.is.tue.mpg.de
Tasks	Optical Flow Estimation, Semantic Segmentation
Published	2017-08-10
URL	http://arxiv.org/abs/1708.03088v1
PDF	http://arxiv.org/pdf/1708.03088v1.pdf
PWC	https://paperswithcode.com/paper/semantic-video-cnns-through-representation
Repo
Framework

An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software


Title	An Analysis of ISO 26262: Using Machine Learning Safely in Automotive Software
Authors	Rick Salay, Rodrigo Queiroz, Krzysztof Czarnecki
Abstract	Machine learning (ML) plays an ever-increasing role in advanced automotive functionality for driver assistance and autonomous operation; however, its adequacy from the perspective of safety certification remains controversial. In this paper, we analyze the impacts that the use of ML as an implementation approach has on ISO 26262 safety lifecycle and ask what could be done to address them. We then provide a set of recommendations on how to adapt the standard to accommodate ML.
Tasks
Published	2017-09-07
URL	http://arxiv.org/abs/1709.02435v1
PDF	http://arxiv.org/pdf/1709.02435v1.pdf
PWC	https://paperswithcode.com/paper/an-analysis-of-iso-26262-using-machine
Repo
Framework

Verb Pattern: A Probabilistic Semantic Representation on Verbs


Title	Verb Pattern: A Probabilistic Semantic Representation on Verbs
Authors	Wanyun Cui, Xiyou Zhou, Hangyu Lin, Yanghua Xiao, Haixun Wang, Seung-won Hwang, Wei Wang
Abstract	Verbs are important in semantic understanding of natural language. Traditional verb representations, such as FrameNet, PropBank, VerbNet, focus on verbs’ roles. These roles are too coarse to represent verbs’ semantics. In this paper, we introduce verb patterns to represent verbs’ semantics, such that each pattern corresponds to a single semantic of the verb. First we analyze the principles for verb patterns: generality and specificity. Then we propose a nonparametric model based on description length. Experimental results prove the high effectiveness of verb patterns. We further apply verb patterns to context-aware conceptualization, to show that verb patterns are helpful in semantic-related tasks.
Tasks
Published	2017-10-20
URL	http://arxiv.org/abs/1710.07695v1
PDF	http://arxiv.org/pdf/1710.07695v1.pdf
PWC	https://paperswithcode.com/paper/verb-pattern-a-probabilistic-semantic
Repo
Framework

Vprop: Variational Inference using RMSprop


Title	Vprop: Variational Inference using RMSprop
Authors	Mohammad Emtiyaz Khan, Zuozhu Liu, Voot Tangkaratt, Yarin Gal
Abstract	Many computationally-efficient methods for Bayesian deep learning rely on continuous optimization algorithms, but the implementation of these methods requires significant changes to existing code-bases. In this paper, we propose Vprop, a method for Gaussian variational inference that can be implemented with two minor changes to the off-the-shelf RMSprop optimizer. Vprop also reduces the memory requirements of Black-Box Variational Inference by half. We derive Vprop using the conjugate-computation variational inference method, and establish its connections to Newton’s method, natural-gradient methods, and extended Kalman filters. Overall, this paper presents Vprop as a principled, computationally-efficient, and easy-to-implement method for Bayesian deep learning.
Tasks
Published	2017-12-04
URL	http://arxiv.org/abs/1712.01038v1
PDF	http://arxiv.org/pdf/1712.01038v1.pdf
PWC	https://paperswithcode.com/paper/vprop-variational-inference-using-rmsprop
Repo
Framework

Weather impacts expressed sentiment


Title	Weather impacts expressed sentiment
Authors	Patrick Baylis, Nick Obradovich, Yury Kryvasheyeu, Haohui Chen, Lorenzo Coviello, Esteban Moro, Manuel Cebrian, James H. Fowler
Abstract	We conduct the largest ever investigation into the relationship between meteorological conditions and the sentiment of human expressions. To do this, we employ over three and a half billion social media posts from tens of millions of individuals from both Facebook and Twitter between 2009 and 2016. We find that cold temperatures, hot temperatures, precipitation, narrower daily temperature ranges, humidity, and cloud cover are all associated with worsened expressions of sentiment, even when excluding weather-related posts. We compare the magnitude of our estimates with the effect sizes associated with notable historical events occurring within our data.
Tasks
Published	2017-08-31
URL	http://arxiv.org/abs/1709.00071v1
PDF	http://arxiv.org/pdf/1709.00071v1.pdf
PWC	https://paperswithcode.com/paper/weather-impacts-expressed-sentiment
Repo
Framework

Propagation via Kernelization: The Vertex Cover Constraint


Title	Propagation via Kernelization: The Vertex Cover Constraint
Authors	Clément Carbonnel, Emmanuel Hébrard
Abstract	The technique of kernelization consists in extracting, from an instance of a problem, an essentially equivalent instance whose size is bounded in a parameter k. Besides being the basis for efficient param-eterized algorithms, this method also provides a wealth of information to reason about in the context of constraint programming. We study the use of kernelization for designing propagators through the example of the Vertex Cover constraint. Since the classic kernelization rules often correspond to dominance rather than consistency, we introduce the notion of “loss-less” kernel. While our preliminary experimental results show the potential of the approach, they also show some of its limits. In particular, this method is more effective for vertex covers of large and sparse graphs, as they tend to have, relatively, smaller kernels.
Tasks
Published	2017-02-07
URL	http://arxiv.org/abs/1702.02470v1
PDF	http://arxiv.org/pdf/1702.02470v1.pdf
PWC	https://paperswithcode.com/paper/propagation-via-kernelization-the-vertex
Repo
Framework

Bayesian Pool-based Active Learning With Abstention Feedbacks


Title	Bayesian Pool-based Active Learning With Abstention Feedbacks
Authors	Cuong V. Nguyen, Lam Si Tung Ho, Huan Xu, Vu Dinh, Binh Nguyen
Abstract	We study pool-based active learning with abstention feedbacks, where a labeler can abstain from labeling a queried example with some unknown abstention rate. This is an important problem with many useful applications. We take a Bayesian approach to the problem and develop two new greedy algorithms that learn both the classification problem and the unknown abstention rate at the same time. These are achieved by simply incorporating the estimated abstention rate into the greedy criteria. We prove that both of our algorithms have near-optimality guarantees: they respectively achieve a ${(1-\frac{1}{e})}$ constant factor approximation of the optimal expected or worst-case value of a useful utility function. Our experiments show the algorithms perform well in various practical scenarios.
Tasks	Active Learning
Published	2017-05-23
URL	http://arxiv.org/abs/1705.08481v2
PDF	http://arxiv.org/pdf/1705.08481v2.pdf
PWC	https://paperswithcode.com/paper/bayesian-pool-based-active-learning-with
Repo
Framework

Automatic Document Image Binarization using Bayesian Optimization


Title	Automatic Document Image Binarization using Bayesian Optimization
Authors	Ekta Vats, Anders Hast, Prashant Singh
Abstract	Document image binarization is often a challenging task due to various forms of degradation. Although there exist several binarization techniques in literature, the binarized image is typically sensitive to control parameter settings of the employed technique. This paper presents an automatic document image binarization algorithm to segment the text from heavily degraded document images. The proposed technique uses a two band-pass filtering approach for background noise removal, and Bayesian optimization for automatic hyperparameter selection for optimal results. The effectiveness of the proposed binarization technique is empirically demonstrated on the Document Image Binarization Competition (DIBCO) and the Handwritten Document Image Binarization Competition (H-DIBCO) datasets.
Tasks
Published	2017-09-06
URL	http://arxiv.org/abs/1709.01782v3
PDF	http://arxiv.org/pdf/1709.01782v3.pdf
PWC	https://paperswithcode.com/paper/automatic-document-image-binarization-using
Repo
Framework

WRPN: Training and Inference using Wide Reduced-Precision Networks


Title	WRPN: Training and Inference using Wide Reduced-Precision Networks
Authors	Asit Mishra, Jeffrey J Cook, Eriko Nurvitadhi, Debbie Marr
Abstract	For computer vision applications, prior works have shown the efficacy of reducing the numeric precision of model parameters (network weights) in deep neural networks but also that reducing the precision of activations hurts model accuracy much more than reducing the precision of model parameters. We study schemes to train networks from scratch using reduced-precision activations without hurting the model accuracy. We reduce the precision of activation maps (along with model parameters) using a novel quantization scheme and increase the number of filter maps in a layer, and find that this scheme compensates or surpasses the accuracy of the baseline full-precision network. As a result, one can significantly reduce the dynamic memory footprint, memory bandwidth, computational energy and speed up the training and inference process with appropriate hardware support. We call our scheme WRPN - wide reduced-precision networks. We report results using our proposed schemes and show that our results are better than previously reported accuracies on ILSVRC-12 dataset while being computationally less expensive compared to previously reported reduced-precision networks.
Tasks	Quantization
Published	2017-04-10
URL	http://arxiv.org/abs/1704.03079v1
PDF	http://arxiv.org/pdf/1704.03079v1.pdf
PWC	https://paperswithcode.com/paper/wrpn-training-and-inference-using-wide
Repo
Framework