January 29, 2020

3421 words 17 mins read

Paper Group ANR 746

Robustification of deep net classifiers by key based diversified aggregation with pre-filtering. Discriminative Principal Component Analysis: A REVERSE THINKING. Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation. Producing Corpora of Medieval and Premodern Occitan. Shape2Motion: Joint Analysis of Motion Parts a …

Robustification of deep net classifiers by key based diversified aggregation with pre-filtering


Title	Robustification of deep net classifiers by key based diversified aggregation with pre-filtering
Authors	Olga Taran, Shideh Rezaeifar, Taras Holotyak, Slava Voloshynovskiy
Abstract	In this paper, we address a problem of machine learning system vulnerability to adversarial attacks. We propose and investigate a Key based Diversified Aggregation (KDA) mechanism as a defense strategy. The KDA assumes that the attacker (i) knows the architecture of classifier and the used defense strategy, (ii) has an access to the training data set but (iii) does not know the secret key. The robustness of the system is achieved by a specially designed key based randomization. The proposed randomization prevents the gradients’ back propagation or the creating of a “bypass” system. The randomization is performed simultaneously in several channels and a multi-channel aggregation stabilizes the results of randomization by aggregating soft outputs from each classifier in multi-channel system. The performed experimental evaluation demonstrates a high robustness and universality of the KDA against the most efficient gradient based attacks like those proposed by N. Carlini and D. Wagner and the non-gradient based sparse adversarial perturbations like OnePixel attacks.
Tasks
Published	2019-05-14
URL	https://arxiv.org/abs/1905.05454v1
PDF	https://arxiv.org/pdf/1905.05454v1.pdf
PWC	https://paperswithcode.com/paper/robustification-of-deep-net-classifiers-by
Repo
Framework

Discriminative Principal Component Analysis: A REVERSE THINKING


Title	Discriminative Principal Component Analysis: A REVERSE THINKING
Authors	Hanli Qiao
Abstract	In this paper, we propose a novel approach named by Discriminative Principal Component Analysis which is abbreviated as Discriminative PCA in order to enhance separability of PCA by Linear Discriminant Analysis (LDA). The proposed method performs feature extraction by determining a linear projection that captures the most scattered discriminative information. The most innovation of Discriminative PCA is performing PCA on discriminative matrix rather than original sample matrix. For calculating the required discriminative matrix under low complexity, we exploit LDA on a converted matrix to obtain within-class matrix and between-class matrix thereof. During the computation process, we utilise direct linear discriminant analysis (DLDA) to solve the encountered SSS problem. For evaluating the performances of Discriminative PCA in face recognition, we analytically compare it with DLAD and PCA on four well known facial databases, they are PIE, FERET, YALE and ORL respectively. Results in accuracy and running time obtained by nearest neighbour classifier are compared when different number of training images per person used. Not only the superiority and outstanding performance of Discriminative PCA showed in recognition rate, but also the comparable results of running time.
Tasks	Face Recognition
Published	2019-03-12
URL	http://arxiv.org/abs/1903.04963v1
PDF	http://arxiv.org/pdf/1903.04963v1.pdf
PWC	https://paperswithcode.com/paper/discriminative-principal-component-analysis-a
Repo
Framework

Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation


Title	Diminishing the Effect of Adversarial Perturbations via Refining Feature Representation
Authors	Nader Asadi, AmirMohammad Sarfi, Mehrdad Hosseinzadeh, Sahba Tahsini, Mahdi Eftekhari
Abstract	Deep neural networks are highly vulnerable to adversarial examples, which imposes severe security issues for these state-of-the-art models. Many defense methods have been proposed to mitigate this problem. However, a lot of them depend on modification or additional training of the target model. In this work, we analytically investigate each layer’s representation of non-perturbed and perturbed images and show the effect of perturbations on each of these representations. Accordingly, a method based on whitening coloring transform is proposed in order to diminish the misrepresentation of any desirable layer caused by adversaries. Our method can be applied to any layer of any arbitrary model without the need of any modification or additional training. Due to the fact that the full whitening of the layer’s representation is not easily differentiable, our proposed method is superbly robust against white-box attacks. Furthermore, we demonstrate the strength of our method against some state-of-the-art black-box attacks.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.01023v2
PDF	https://arxiv.org/pdf/1907.01023v2.pdf
PWC	https://paperswithcode.com/paper/diminishing-the-effect-of-adversarial
Repo
Framework

Producing Corpora of Medieval and Premodern Occitan


Title	Producing Corpora of Medieval and Premodern Occitan
Authors	Jean-Baptiste Camps, Gilles Guilhem Couffignal
Abstract	At a time when the quantity of - more or less freely - available data is increasing significantly, thanks to digital corpora, editions or libraries, the development of data mining tools or deep learning methods allows researchers to build a corpus of study tailored for their research, to enrich their data and to exploit them.Open optical character recognition (OCR) tools can be adapted to old prints, incunabula or even manuscripts, with usable results, allowing the rapid creation of textual corpora. The alternation of training and correction phases makes it possible to improve the quality of the results by rapidly accumulating raw text data. These can then be structured, for example in XML/TEI, and enriched.The enrichment of the texts with graphic or linguistic annotations can also be automated. These processes, known to linguists and functional for modern languages, present difficulties for languages such as Medieval Occitan, due in part to the absence of big enough lemmatized corpora. Suggestions for the creation of tools adapted to the considerable spelling variation of ancient languages will be presented, as well as experiments for the lemmatization of Medieval and Premodern Occitan.These techniques open the way for many exploitations. The much desired increase in the amount of available quality texts and data makes it possible to improve digital philology methods, if everyone takes the trouble to make their data freely available online and reusable.By exposing different technical solutions and some micro-analyses as examples, this paper aims to show part of what digital philology can offer to researchers in the Occitan domain, while recalling the ethical issues on which such practices are based.
Tasks	Lemmatization, Optical Character Recognition
Published	2019-04-26
URL	http://arxiv.org/abs/1904.11815v1
PDF	http://arxiv.org/pdf/1904.11815v1.pdf
PWC	https://paperswithcode.com/paper/producing-corpora-of-medieval-and-premodern
Repo
Framework

Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes


Title	Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
Authors	Xiaogang Wang, Bin Zhou, Yahao Shi, Xiaowu Chen, Qinping Zhao, Kai Xu
Abstract	For the task of mobility analysis of 3D shapes, we propose joint analysis for simultaneous motion part segmentation and motion attribute estimation, taking a single 3D model as input. The problem is significantly different from those tackled in the existing works which assume the availability of either a pre-existing shape segmentation or multiple 3D models in different motion states. To that end, we develop Shape2Motion which takes a single 3D point cloud as input, and jointly computes a mobility-oriented segmentation and the associated motion attributes. Shape2Motion is comprised of two deep neural networks designed for mobility proposal generation and mobility optimization, respectively. The key contribution of these networks is the novel motion-driven features and losses used in both motion part segmentation and motion attribute estimation. This is based on the observation that the movement of a functional part preserves the shape structure. We evaluate Shape2Motion with a newly proposed benchmark for mobility analysis of 3D shapes. Results demonstrate that our method achieves the state-of-the-art performance both in terms of motion part segmentation and motion attribute estimation.
Tasks
Published	2019-03-10
URL	http://arxiv.org/abs/1903.03911v2
PDF	http://arxiv.org/pdf/1903.03911v2.pdf
PWC	https://paperswithcode.com/paper/shape2motion-joint-analysis-of-motion-parts
Repo
Framework

TAPESTRY: A Blockchain based Service for Trusted Interaction Online


Title	TAPESTRY: A Blockchain based Service for Trusted Interaction Online
Authors	Yifan Yang, Daniel Cooper, John Collomosse, Constantin C. Drăgan, Mark Manulis, Jamie Steane, Arthi Manohar, Jo Briggs, Helen Jones, Wendy Moncur
Abstract	We present a novel blockchain based service for proving the provenance of online digital identity, exposed as an assistive tool to help non-expert users make better decisions about whom to trust online. Our service harnesses the digital personhood (DP); the longitudinal and multi-modal signals created through users’ lifelong digital interactions, as a basis for evidencing the provenance of identity. We describe how users may exchange trust evidence derived from their DP, in a granular and privacy-preserving manner, with other users in order to demonstrate coherence and longevity in their behaviour online. This is enabled through a novel secure infrastructure combining hybrid on- and off-chain storage combined with deep learning for DP analytics and visualization. We show how our tools enable users to make more effective decisions on whether to trust unknown third parties online, and also to spot behavioural deviations in their own social media footprints indicative of account hijacking.
Tasks
Published	2019-05-15
URL	http://arxiv.org/abs/1905.06186v1
PDF	http://arxiv.org/pdf/1905.06186v1.pdf
PWC	https://paperswithcode.com/paper/tapestry-a-blockchain-based-service-for
Repo
Framework

Discriminant analysis based on projection onto generalized difference subspace


Title	Discriminant analysis based on projection onto generalized difference subspace
Authors	Kazuhiro Fukui, Naoya Sogi, Takumi Kobayashi, Jing-Hao Xue, Atsuto Maki
Abstract	This paper discusses a new type of discriminant analysis based on the orthogonal projection of data onto a generalized difference subspace (GDS). In our previous work, we have demonstrated that GDS projection works as the quasi-orthogonalization of class subspaces, which is an effective feature extraction for subspace based classifiers. Interestingly, GDS projection also works as a discriminant feature extraction through a similar mechanism to the Fisher discriminant analysis (FDA). A direct proof of the connection between GDS projection and FDA is difficult due to the significant difference in their formulations. To avoid the difficulty, we first introduce geometrical Fisher discriminant analysis (gFDA) based on a simplified Fisher criterion. Our simplified Fisher criterion is derived from a heuristic yet practically plausible principle: the direction of the sample mean vector of a class is in most cases almost equal to that of the first principal component vector of the class, under the condition that the principal component vectors are calculated by applying the principal component analysis (PCA) without data centering. gFDA can work stably even under few samples, bypassing the small sample size (SSS) problem of FDA. Next, we prove that gFDA is equivalent to GDS projection with a small correction term. This equivalence ensures GDS projection to inherit the discriminant ability from FDA via gFDA. Furthermore, to enhance the performances of gFDA and GDS projection, we normalize the projected vectors on the discriminant spaces. Extensive experiments using the extended Yale B+ database and the CMU face database show that gFDA and GDS projection have equivalent or better performance than the original FDA and its extensions.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13113v2
PDF	https://arxiv.org/pdf/1910.13113v2.pdf
PWC	https://paperswithcode.com/paper/discriminant-analysis-based-on-projection
Repo
Framework


Title	Sentiment Analysis of Typhoon Related Tweets using Standard and Bidirectional Recurrent Neural Networks
Authors	Joseph Marvin Imperial, Jeyrome Orosco, Shiela Mae Mazo, Lany Maceda
Abstract	The Philippines is a common ground to natural calamities like typhoons, floods, volcanic eruptions and earthquakes. With Twitter as one of the most used social media platform in the Philippines, a total of 39,867 preprocessed tweets were obtained given a time frame starting from November 1, 2013 to January 31, 2014. Sentiment analysis determines the underlying emotion given a series of words. The main purpose of this study is to identify the sentiments expressed in the tweets sent by the Filipino people before, during, and after Typhoon Yolanda using two variations of Recurrent Neural Networks; standard and bidirectional. The best generated models after training with various hyperparameters achieved a high accuracy of 81.79% for fine-grained classification using standard RNN and 87.69% for binary classification using bidirectional RNN. Findings revealed that 51.1% of the tweets sent were positive expressing support, love, and words of courage to the victims; 19.8% were negative stating sadness and despair for the loss of lives and hate for corrupt officials; while the other 29% were neutral tweets from local news stations, announcements of relief operations, donation drives, and observations by citizens.
Tasks	Sentiment Analysis
Published	2019-08-03
URL	https://arxiv.org/abs/1908.01765v1
PDF	https://arxiv.org/pdf/1908.01765v1.pdf
PWC	https://paperswithcode.com/paper/sentiment-analysis-of-typhoon-related-tweets
Repo
Framework

Learning to Reformulate the Queries on the WEB


Title	Learning to Reformulate the Queries on the WEB
Authors	Amir H. Jadidinejad
Abstract	Inability of the naive users to formulate appropriate queries is a fundamental problem in web search engines. Therefore, assisting users to issue more effective queries is an important way to improve users’ happiness. One effective approach is query reformulation, which generates new effective queries according to the current query issued by users. Previous researches typically generate words and phrases related to the original query. Since the definition of query reformulation is quite general, it is completely difficult to develop a uniform term-based approach for this problem. This paper uses readily available data, particularly over one billion anchor phrases in Clueweb09 corpus, in order to learn an end-to-end encoder-decoder model to automatically generate effective queries. Following successful researches in the field of sequence to sequence models, we employ a character-level convolutional neural network with max-pooling at encoder and an attention-based recurrent neural network at decoder. The whole model learned in an unsupervised end-to-end manner.Experiments on TREC collections show that the reformulated queries automatically generated by the proposed solution can significantly improve the retrieval performance.
Tasks
Published	2019-07-02
URL	https://arxiv.org/abs/1907.01300v1
PDF	https://arxiv.org/pdf/1907.01300v1.pdf
PWC	https://paperswithcode.com/paper/learning-to-reformulate-the-queries-on-the
Repo
Framework

Memorizing All for Implicit Discourse Relation Recognition


Title	Memorizing All for Implicit Discourse Relation Recognition
Authors	Hongxiao Bai, Hai Zhao, Junhan Zhao
Abstract	Implicit discourse relation recognition is a challenging task due to the absence of the necessary informative clue from explicit connectives. The prediction of relations requires a deep understanding of the semantic meanings of sentence pairs. As implicit discourse relation recognizer has to carefully tackle the semantic similarity of the given sentence pairs and the severe data sparsity issue exists in the meantime, it is supposed to be beneficial from mastering the entire training data. Thus in this paper, we propose a novel memory mechanism to tackle the challenges for further performance improvement. The memory mechanism is adequately memorizing information by pairing representations and discourse relations of all training instances, which right fills the slot of the data-hungry issue in the current implicit discourse relation recognizer. Our experiments show that our full model with memorizing the entire training set reaches new state-of-the-art against strong baselines, which especially for the first time exceeds the milestone of 60% accuracy in the 4-way task.
Tasks	Semantic Similarity, Semantic Textual Similarity
Published	2019-08-29
URL	https://arxiv.org/abs/1908.11317v1
PDF	https://arxiv.org/pdf/1908.11317v1.pdf
PWC	https://paperswithcode.com/paper/memorizing-all-for-implicit-discourse
Repo
Framework

Ordering Matters: Word Ordering Aware Unsupervised NMT


Title	Ordering Matters: Word Ordering Aware Unsupervised NMT
Authors	Tamali Banerjee, Rudra Murthy V, Pushpak Bhattacharyya
Abstract	Denoising-based Unsupervised Neural Machine Translation (U-NMT) models typically employ denoising strategy at the encoder module to prevent the model from memorizing the input source sentence. Specifically, given an input sentence of length n, the model applies n/2 random swaps between consecutive words and trains the denoising-based U-NMT model. Though effective, applying denoising strategy on every sentence in the training data leads to uncertainty in the model thereby, limiting the benefits from the denoising-based U-NMT model. In this paper, we propose a simple fine-tuning strategy where we fine-tune the trained denoising-based U-NMT system without the denoising strategy. The input sentences are presented as is i.e., without any shuffling noise added. We observe significant improvements in translation performance on many language pairs from our fine-tuning strategy. Our analysis reveals that our proposed models lead to increase in higher n-gram BLEU score compared to the denoising U-NMT models.
Tasks	Denoising, Machine Translation
Published	2019-10-30
URL	https://arxiv.org/abs/1911.01212v1
PDF	https://arxiv.org/pdf/1911.01212v1.pdf
PWC	https://paperswithcode.com/paper/ordering-matters-word-ordering-aware
Repo
Framework

Learning from Sets of Items in Recommender Systems


Title	Learning from Sets of Items in Recommender Systems
Authors	Mohit Sharma, F. Maxwell Harper, George Karypis
Abstract	Most of the existing recommender systems use the ratings provided by users on individual items. An additional source of preference information is to use the ratings that users provide on sets of items. The advantages of using preferences on sets are two-fold. First, a rating provided on a set conveys some preference information about each of the set’s items, which allows us to acquire a user’s preferences for more items that the number of ratings that the user provided. Second, due to privacy concerns, users may not be willing to reveal their preferences on individual items explicitly but may be willing to provide a single rating to a set of items, since it provides some level of information hiding. This paper investigates two questions related to using set-level ratings in recommender systems. First, how users’ item-level ratings relate to their set-level ratings. Second, how collaborative filtering-based models for item-level rating prediction can take advantage of such set-level ratings. We have collected set-level ratings from active users of Movielens on sets of movies that they have rated in the past. Our analysis of these ratings shows that though the majority of the users provide the average of the ratings on a set’s constituent items as the rating on the set, there exists a significant number of users that tend to consistently either under- or over-rate the sets. We have developed collaborative filtering-based methods to explicitly model these user behaviors that can be used to recommend items to users. Experiments on real data and on synthetic data that resembles the under- or over-rating behavior in the real data, demonstrate that these models can recover the overall characteristics of the underlying data and predict the user’s ratings on individual items.
Tasks	Recommendation Systems
Published	2019-04-22
URL	http://arxiv.org/abs/1904.12643v1
PDF	http://arxiv.org/pdf/1904.12643v1.pdf
PWC	https://paperswithcode.com/paper/190412643
Repo
Framework

CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology


Title	CMU-01 at the SIGMORPHON 2019 Shared Task on Crosslinguality and Context in Morphology
Authors	Aditi Chaudhary, Elizabeth Salesky, Gayatri Bhat, David R. Mortensen, Jaime G. Carbonell, Yulia Tsvetkov
Abstract	This paper presents the submission by the CMU-01 team to the SIGMORPHON 2019 task 2 of Morphological Analysis and Lemmatization in Context. This task requires us to produce the lemma and morpho-syntactic description of each token in a sequence, for 107 treebanks. We approach this task with a hierarchical neural conditional random field (CRF) model which predicts each coarse-grained feature (eg. POS, Case, etc.) independently. However, most treebanks are under-resourced, thus making it challenging to train deep neural models for them. Hence, we propose a multi-lingual transfer training regime where we transfer from multiple related languages that share similar typology.
Tasks	Lemmatization, Morphological Analysis
Published	2019-07-23
URL	https://arxiv.org/abs/1907.10129v1
PDF	https://arxiv.org/pdf/1907.10129v1.pdf
PWC	https://paperswithcode.com/paper/cmu-01-at-the-sigmorphon-2019-shared-task-on
Repo
Framework

Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling


Title	Generalizable Adversarial Attacks with Latent Variable Perturbation Modelling
Authors	Avishek Joey Bose, Andre Cianflone, William L. Hamilton
Abstract	Adversarial attacks on deep neural networks traditionally rely on a constrained optimization paradigm, where an optimization procedure is used to obtain a single adversarial perturbation for a given input example. In this work we frame the problem as learning a distribution of adversarial perturbations, enabling us to generate diverse adversarial distributions given an unperturbed input. We show that this framework is domain-agnostic in that the same framework can be employed to attack different input domains with minimal modification. Across three diverse domains—images, text, and graphs—our approach generates whitebox attacks with success rates that are competitive with or superior to existing approaches, with a new state-of-the-art achieved in the graph domain. Finally, we demonstrate that our framework can efficiently generate a diverse set of attacks for a single given input, and is even capable of attacking \textit{unseen} test instances in a zero-shot manner, exhibiting attack generalization.
Tasks
Published	2019-05-26
URL	https://arxiv.org/abs/1905.10864v3
PDF	https://arxiv.org/pdf/1905.10864v3.pdf
PWC	https://paperswithcode.com/paper/generalizable-adversarial-attacks-using
Repo
Framework

Semi- and Weakly-supervised Human Pose Estimation


Title	Semi- and Weakly-supervised Human Pose Estimation
Authors	Norimichi Ukita, Yusuke Uematsu
Abstract	For human pose estimation in still images, this paper proposes three semi- and weakly-supervised learning schemes. While recent advances of convolutional neural networks improve human pose estimation using supervised training data, our focus is to explore the semi- and weakly-supervised schemes. Our proposed schemes initially learn conventional model(s) for pose estimation from a small amount of standard training images with human pose annotations. For the first semi-supervised learning scheme, this conventional pose model detects candidate poses in training images with no human annotation. From these candidate poses, only true-positives are selected by a classifier using a pose feature representing the configuration of all body parts. The accuracies of these candidate pose estimation and true-positive pose selection are improved by action labels provided to these images in our second and third learning schemes, which are semi- and weakly-supervised learning. While the first and second learning schemes select only poses that are similar to those in the supervised training data, the third scheme selects more true-positive poses that are significantly different from any supervised poses. This pose selection is achieved by pose clustering using outlier pose detection with Dirichlet process mixtures and the Bayes factor. The proposed schemes are validated with large-scale human pose datasets.
Tasks	Pose Estimation
Published	2019-06-04
URL	https://arxiv.org/abs/1906.01399v1
PDF	https://arxiv.org/pdf/1906.01399v1.pdf
PWC	https://paperswithcode.com/paper/semi-and-weakly-supervised-human-pose
Repo
Framework