October 16, 2019

3094 words 15 mins read

Paper Group ANR 1101

Image denoising through bivariate shrinkage function in framelet domain. Mitigation of Adversarial Attacks through Embedded Feature Selection. Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing. A NoSQL Data-based Personalized Recommendation System for C2C e-Commerce. Real-Valued Evolutio …

Image denoising through bivariate shrinkage function in framelet domain


Title	Image denoising through bivariate shrinkage function in framelet domain
Authors	Hamid Reza Shahdoosti
Abstract	Denoising of coefficients in a sparse domain (e.g. wavelet) has been researched extensively because of its simplicity and effectiveness. Literature mainly has focused on designing the best global threshold. However, this paper proposes a new denoising method using bivariate shrinkage function in framelet domain. In the proposed method, maximum aposteriori probability is used for estimate of the denoised coefficient and non-Gaussian bivariate function is applied to model the statistics of framelet coefficients. For every framelet coefficient, there is a corresponding threshold depending on the local statistics of framelet coefficients. Experimental results show that using bivariate shrinkage function in framelet domain yields significantly superior image quality and higher PSNR than some well-known denoising methods.
Tasks	Denoising, Image Denoising
Published	2018-01-02
URL	http://arxiv.org/abs/1801.00635v1
PDF	http://arxiv.org/pdf/1801.00635v1.pdf
PWC	https://paperswithcode.com/paper/image-denoising-through-bivariate-shrinkage
Repo
Framework

Mitigation of Adversarial Attacks through Embedded Feature Selection


Title	Mitigation of Adversarial Attacks through Embedded Feature Selection
Authors	Ziyi Bao, Luis Muñoz-González, Emil C. Lupu
Abstract	Machine learning has become one of the main components for task automation in many application domains. Despite the advancements and impressive achievements of machine learning, it has been shown that learning algorithms can be compromised by attackers both at training and test time. Machine learning systems are especially vulnerable to adversarial examples where small perturbations added to the original data points can produce incorrect or unexpected outputs in the learning algorithms at test time. Mitigation of these attacks is hard as adversarial examples are difficult to detect. Existing related work states that the security of machine learning systems against adversarial examples can be weakened when feature selection is applied to reduce the systems’ complexity. In this paper, we empirically disprove this idea, showing that the relative distortion that the attacker has to introduce to succeed in the attack is greater when the target is using a reduced set of features. We also show that the minimal adversarial examples differ statistically more strongly from genuine examples with a lower number of features. However, reducing the feature count can negatively impact the system’s performance. We illustrate the trade-off between security and accuracy with specific examples. We propose a design methodology to evaluate the security of machine learning classifiers with embedded feature selection against adversarial examples crafted using different attack strategies.
Tasks	Feature Selection
Published	2018-08-16
URL	http://arxiv.org/abs/1808.05705v1
PDF	http://arxiv.org/pdf/1808.05705v1.pdf
PWC	https://paperswithcode.com/paper/mitigation-of-adversarial-attacks-through
Repo
Framework

Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing


Title	Modeling Language Variation and Universals: A Survey on Typological Linguistics for Natural Language Processing
Authors	Edoardo Maria Ponti, Helen O’Horan, Yevgeni Berzak, Ivan Vulić, Roi Reichart, Thierry Poibeau, Ekaterina Shutova, Anna Korhonen
Abstract	Linguistic typology aims to capture structural and semantic variation across the world’s languages. A large-scale typology could provide excellent guidance for multilingual Natural Language Processing (NLP), particularly for languages that suffer from the lack of human labeled resources. We present an extensive literature survey on the use of typological information in the development of NLP techniques. Our survey demonstrates that to date, the use of information in existing typological databases has resulted in consistent but modest improvements in system performance. We show that this is due to both intrinsic limitations of databases (in terms of coverage and feature granularity) and under-employment of the typological features included in them. We advocate for a new approach that adapts the broad and discrete nature of typological categories to the contextual and continuous nature of machine learning algorithms used in contemporary NLP. In particular, we suggest that such approach could be facilitated by recent developments in data-driven induction of typological knowledge.
Tasks	Cross-Lingual Transfer
Published	2018-07-02
URL	http://arxiv.org/abs/1807.00914v2
PDF	http://arxiv.org/pdf/1807.00914v2.pdf
PWC	https://paperswithcode.com/paper/modeling-language-variation-and-universals-a
Repo
Framework

A NoSQL Data-based Personalized Recommendation System for C2C e-Commerce


Title	A NoSQL Data-based Personalized Recommendation System for C2C e-Commerce
Authors	Khanh Dang, Khuong Vo, Josef Küng
Abstract	With the considerable development of customer-to-customer (C2C) e-commerce in the recent years, there is a big demand for an effective recommendation system that suggests suitable websites for users to sell their items with some specified needs. Nonetheless, e-commerce recommendation systems are mostly designed for business-to-customer (B2C) websites, where the systems offer the consumers the products that they might like to buy. Almost none of the related research works focus on choosing selling sites for target items. In this paper, we introduce an approach that recommends the selling websites based upon the item’s description, category, and desired selling price. This approach employs NoSQL data-based machine learning techniques for building and training topic models and classification models. The trained models can then be used to rank the websites dynamically with respect to the user needs. The experimental results with real-world datasets from Vietnam C2C websites will demonstrate the effectiveness of our proposed method.
Tasks	Recommendation Systems, Topic Models
Published	2018-06-26
URL	http://arxiv.org/abs/1806.09793v1
PDF	http://arxiv.org/pdf/1806.09793v1.pdf
PWC	https://paperswithcode.com/paper/a-nosql-data-based-personalized
Repo
Framework


Title	Real-Valued Evolutionary Multi-Modal Optimization driven by Hill-Valley Clustering
Authors	S. C. Maree, T. Alderliesten, D. Thierens, P. A. N. Bosman
Abstract	Model-based evolutionary algorithms (EAs) adapt an underlying search model to features of the problem at hand, such as the linkage between problem variables. The performance of EAs often deteriorates as multiple modes in the fitness landscape are modelled with a unimodal search model. The number of modes is however often unknown a priori, especially in a black-box setting, which complicates adaptation of the search model. In this work, we focus on models that can adapt to the multi-modality of the fitness landscape. Specifically, we introduce Hill-Valley Clustering, a remarkably simple approach to adaptively cluster the search space in niches, such that a single mode resides in each niche. In each of the located niches, a core search algorithm is initialized to optimize that niche. Combined with an EA and a restart scheme, the resulting Hill-Valley EA (HillVallEA) is compared to current state-of-the-art niching methods on a standard benchmark suite for multi-modal optimization. Numerical results in terms of the detected number of global optima show that, in spite of its simplicity, HillVallEA is competitive within the limited budget of the benchmark suite, and shows superior performance in the long run.
Tasks
Published	2018-10-16
URL	http://arxiv.org/abs/1810.07085v1
PDF	http://arxiv.org/pdf/1810.07085v1.pdf
PWC	https://paperswithcode.com/paper/real-valued-evolutionary-multi-modal
Repo
Framework

Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps


Title	Real-time Dynamic Object Detection for Autonomous Driving using Prior 3D-Maps
Authors	B Ravi Kiran, Luis Roldão, Benat Irastorza, Renzo Verastegui, Sebastian Suss, Senthil Yogamani, Victor Talpaert, Alexandre Lepoutre, Guillaume Trehard
Abstract	Lidar has become an essential sensor for autonomous driving as it provides reliable depth estimation. Lidar is also the primary sensor used in building 3D maps which can be used even in the case of low-cost systems which do not use Lidar. Computation on Lidar point clouds is intensive as it requires processing of millions of points per second. Additionally there are many subsequent tasks such as clustering, detection, tracking and classification which makes real-time execution challenging. In this paper, we discuss real-time dynamic object detection algorithms which leverages previously mapped Lidar point clouds to reduce processing. The prior 3D maps provide a static background model and we formulate dynamic object detection as a background subtraction problem. Computation and modeling challenges in the mapping and online execution pipeline are described. We propose a rejection cascade architecture to subtract road regions and other 3D regions separately. We implemented an initial version of our proposed algorithm and evaluated the accuracy on CARLA simulator.
Tasks	Autonomous Driving, Depth Estimation, Object Detection
Published	2018-09-28
URL	https://arxiv.org/abs/1809.11036v2
PDF	https://arxiv.org/pdf/1809.11036v2.pdf
PWC	https://paperswithcode.com/paper/real-time-dynamic-object-detection-for
Repo
Framework

Optimal Hierarchical Learning Path Design with Reinforcement Learning


Title	Optimal Hierarchical Learning Path Design with Reinforcement Learning
Authors	Xiao Li, Hanchen Xu, Jinming Zhang, Hua-hua Chang
Abstract	E-learning systems are capable of providing more adaptive and efficient learning experiences for students than the traditional classroom setting. A key component of such systems is the learning strategy, the algorithm that designs the learning paths for students based on information such as the students’ current progresses, their skills, learning materials, and etc. In this paper, we address the problem of finding the optimal learning strategy for an E-learning system. To this end, we first develop a model for students’ hierarchical skills in the E-learning system. Based on the hierarchical skill model and the classical cognitive diagnosis model, we further develop a framework to model various proficiency levels of hierarchical skills. The optimal learning strategy on top of the hierarchical structure is found by applying a model-free reinforcement learning method, which does not require information on students’ learning transition process. The effectiveness of the proposed framework is demonstrated via numerical experiments.
Tasks
Published	2018-10-12
URL	http://arxiv.org/abs/1810.05347v1
PDF	http://arxiv.org/pdf/1810.05347v1.pdf
PWC	https://paperswithcode.com/paper/optimal-hierarchical-learning-path-design
Repo
Framework

P2P-NET: Bidirectional Point Displacement Net for Shape Transform


Title	P2P-NET: Bidirectional Point Displacement Net for Shape Transform
Authors	Kangxue Yin, Hui Huang, Daniel Cohen-Or, Hao Zhang
Abstract	We introduce P2P-NET, a general-purpose deep neural network which learns geometric transformations between point-based shape representations from two domains, e.g., meso-skeletons and surfaces, partial and complete scans, etc. The architecture of the P2P-NET is that of a bi-directional point displacement network, which transforms a source point set to a target point set with the same cardinality, and vice versa, by applying point-wise displacement vectors learned from data. P2P-NET is trained on paired shapes from the source and target domains, but without relying on point-to-point correspondences between the source and target point sets. The training loss combines two uni-directional geometric losses, each enforcing a shape-wise similarity between the predicted and the target point sets, and a cross-regularization term to encourage consistency between displacement vectors going in opposite directions. We develop and present several different applications enabled by our general-purpose bidirectional P2P-NET to highlight the effectiveness, versatility, and potential of our network in solving a variety of point-based shape transformation problems.
Tasks
Published	2018-03-25
URL	http://arxiv.org/abs/1803.09263v4
PDF	http://arxiv.org/pdf/1803.09263v4.pdf
PWC	https://paperswithcode.com/paper/p2p-net-bidirectional-point-displacement-net
Repo
Framework

Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT


Title	Multi-representation Ensembles and Delayed SGD Updates Improve Syntax-based NMT
Authors	Danielle Saunders, Felix Stahlberg, Adria de Gispert, Bill Byrne
Abstract	We explore strategies for incorporating target syntax into Neural Machine Translation. We specifically focus on syntax in ensembles containing multiple sentence representations. We formulate beam search over such ensembles using WFSTs, and describe a delayed SGD update training procedure that is especially effective for long representations like linearized syntax. Our approach gives state-of-the-art performance on a difficult Japanese-English task.
Tasks	Machine Translation
Published	2018-05-01
URL	http://arxiv.org/abs/1805.00456v3
PDF	http://arxiv.org/pdf/1805.00456v3.pdf
PWC	https://paperswithcode.com/paper/multi-representation-ensembles-and-delayed
Repo
Framework

High-Resolution Talking Face Generation via Mutual Information Approximation


Title	High-Resolution Talking Face Generation via Mutual Information Approximation
Authors	Hao Zhu, Aihua Zheng, Huaibo Huang, Ran He
Abstract	Given an arbitrary speech clip and a facial image, talking face generation aims to synthesize a talking face video with precise lip synchronization as well as a smooth transition of facial motion over the entire video speech. Most existing methods mainly focus on either disentangling the information in a single image or learning temporal information between frames. However, speech audio and video often have cross-modality coherence that has not been well addressed during synthesis. Therefore, this paper proposes a novel high-resolution talking face generation model for arbitrary person by discovering the cross-modality coherence via Mutual Information Approximation (MIA). By assuming the modality difference between audio and video is larger that of real video and generated video, we estimate mutual information between real audio and video, and then use a discriminator to enforce generated video distribution approach real video distribution. Furthermore, we introduce a dynamic attention technique on the mouth to enhance the robustness during the training stage. Experimental results on benchmark dataset LRW transcend the state-of-the-art methods on prevalent metrics with robustness on gender, pose variations and high-resolution synthesizing.
Tasks	Face Generation, Talking Face Generation
Published	2018-12-17
URL	http://arxiv.org/abs/1812.06589v1
PDF	http://arxiv.org/pdf/1812.06589v1.pdf
PWC	https://paperswithcode.com/paper/high-resolution-talking-face-generation-via
Repo
Framework

Reliable Semi-Supervised Learning when Labels are Missing at Random


Title	Reliable Semi-Supervised Learning when Labels are Missing at Random
Authors	Xiuming Liu, Dave Zachariah, Johan Wågberg, Thomas B. Schön
Abstract	Semi-supervised learning methods are motivated by the availability of large datasets with unlabeled features in addition to labeled data. Unlabeled data is, however, not guaranteed to improve classification performance and has in fact been reported to impair the performance in certain cases. A fundamental source of error arises from restrictive assumptions about the unlabeled features, which result in unreliable classifiers that underestimate their prediction error probabilities. In this paper, we develop a semi-supervised learning approach that relaxes such assumptions and is capable of providing classifiers that reliably quantify the label uncertainty. The approach is applicable using any generative model with a supervised learning algorithm. We illustrate the approach using both handwritten digit and cloth classification data where the labels are missing at random.
Tasks
Published	2018-11-27
URL	https://arxiv.org/abs/1811.10947v5
PDF	https://arxiv.org/pdf/1811.10947v5.pdf
PWC	https://paperswithcode.com/paper/reliable-semi-supervised-learning-when-labels
Repo
Framework

Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships


Title	Improving the Coverage and the Generalization Ability of Neural Word Sense Disambiguation through Hypernymy and Hyponymy Relationships
Authors	Loïc Vial, Benjamin Lecouteux, Didier Schwab
Abstract	In Word Sense Disambiguation (WSD), the predominant approach generally involves a supervised system trained on sense annotated corpora. The limited quantity of such corpora however restricts the coverage and the performance of these systems. In this article, we propose a new method that solves these issues by taking advantage of the knowledge present in WordNet, and especially the hypernymy and hyponymy relationships between synsets, in order to reduce the number of different sense tags that are necessary to disambiguate all words of the lexical database. Our method leads to state of the art results on most WSD evaluation tasks, while improving the coverage of supervised systems, reducing the training time and the size of the models, without additional training data. In addition, we exhibit results that significantly outperform the state of the art when our method is combined with an ensembling technique and the addition of the WordNet Gloss Tagged as training corpus.
Tasks	Word Sense Disambiguation
Published	2018-11-02
URL	http://arxiv.org/abs/1811.00960v1
PDF	http://arxiv.org/pdf/1811.00960v1.pdf
PWC	https://paperswithcode.com/paper/improving-the-coverage-and-the-generalization
Repo
Framework

Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation


Title	Quantization of Fully Convolutional Networks for Accurate Biomedical Image Segmentation
Authors	Xiaowei Xu, Qing Lu, Yu Hu, Lin Yang, Sharon Hu, Danny Chen, Yiyu Shi
Abstract	With pervasive applications of medical imaging in health-care, biomedical image segmentation plays a central role in quantitative analysis, clinical diagno- sis, and medical intervention. Since manual anno- tation su ers limited reproducibility, arduous e orts, and excessive time, automatic segmentation is desired to process increasingly larger scale histopathological data. Recently, deep neural networks (DNNs), par- ticularly fully convolutional networks (FCNs), have been widely applied to biomedical image segmenta- tion, attaining much improved performance. At the same time, quantization of DNNs has become an ac- tive research topic, which aims to represent weights with less memory (precision) to considerably reduce memory and computation requirements of DNNs while maintaining acceptable accuracy. In this paper, we apply quantization techniques to FCNs for accurate biomedical image segmentation. Unlike existing litera- ture on quantization which primarily targets memory and computation complexity reduction, we apply quan- tization as a method to reduce over tting in FCNs for better accuracy. Speci cally, we focus on a state-of- the-art segmentation framework, suggestive annotation [22], which judiciously extracts representative annota- tion samples from the original training dataset, obtain- ing an e ective small-sized balanced training dataset. We develop two new quantization processes for this framework: (1) suggestive annotation with quantiza- tion for highly representative training samples, and (2) network training with quantization for high accuracy. Extensive experiments on the MICCAI Gland dataset show that both quantization processes can improve the segmentation performance, and our proposed method exceeds the current state-of-the-art performance by up to 1%. In addition, our method has a reduction of up to 6.4x on memory usage.
Tasks	Quantization, Semantic Segmentation
Published	2018-03-13
URL	http://arxiv.org/abs/1803.04907v1
PDF	http://arxiv.org/pdf/1803.04907v1.pdf
PWC	https://paperswithcode.com/paper/quantization-of-fully-convolutional-networks
Repo
Framework

Can I trust you more? Model-Agnostic Hierarchical Explanations


Title	Can I trust you more? Model-Agnostic Hierarchical Explanations
Authors	Michael Tsang, Youbang Sun, Dongxu Ren, Yan Liu
Abstract	Interactions such as double negation in sentences and scene interactions in images are common forms of complex dependencies captured by state-of-the-art machine learning models. We propose Mah'e, a novel approach to provide Model-agnostic hierarchical 'explanations of how powerful machine learning models, such as deep neural networks, capture these interactions as either dependent on or free of the context of data instances. Specifically, Mah'e provides context-dependent explanations by a novel local interpretation algorithm that effectively captures any-order interactions, and obtains context-free explanations through generalizing context-dependent interactions to explain global behaviors. Experimental results show that Mah'e obtains improved local interaction interpretations over state-of-the-art methods and successfully explains interactions that are context-free.
Tasks
Published	2018-12-12
URL	http://arxiv.org/abs/1812.04801v1
PDF	http://arxiv.org/pdf/1812.04801v1.pdf
PWC	https://paperswithcode.com/paper/can-i-trust-you-more-model-agnostic
Repo
Framework

Using Discretization for Extending the Set of Predictive Features


Title	Using Discretization for Extending the Set of Predictive Features
Authors	Avi Rosenfeld, Ron Illuz, Dovid Gottesman, Mark Last
Abstract	To date, attribute discretization is typically performed by replacing the original set of continuous features with a transposed set of discrete ones. This paper provides support for a new idea that discretized features should often be used in addition to existing features and as such, datasets should be extended, and not replaced, by discretization. We also claim that discretization algorithms should be developed with the explicit purpose of enriching a non-discretized dataset with discretized values. We present such an algorithm, D-MIAT, a supervised algorithm that discretizes data based on Minority Interesting Attribute Thresholds. D-MIAT only generates new features when strong indications exist for one of the target values needing to be learned and thus is intended to be used in addition to the original data. We present extensive empirical results demonstrating the success of using D-MIAT on $ 28 $ benchmark datasets. We also demonstrate that $ 10 $ other discretization algorithms can also be used to generate features that yield improved performance when used in combination with the original non-discretized data. Our results show that the best predictive performance is attained using a combination of the original dataset with added features from a “standard” supervised discretization algorithm and D-MIAT.
Tasks
Published	2018-02-09
URL	http://arxiv.org/abs/1802.03239v1
PDF	http://arxiv.org/pdf/1802.03239v1.pdf
PWC	https://paperswithcode.com/paper/using-discretization-for-extending-the-set-of
Repo
Framework