January 31, 2020

3283 words 16 mins read

Paper Group AWR 391

Combination of Multiple Global Descriptors for Image Retrieval. Testing Robustness Against Unforeseen Adversaries. A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection. Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians. Adversarial Defense by Restricting the Hidden Space of Deep Neural …

Combination of Multiple Global Descriptors for Image Retrieval


Title	Combination of Multiple Global Descriptors for Image Retrieval
Authors	HeeJae Jun, ByungSoo Ko, Youngjoon Kim, Insik Kim, Jongtack Kim
Abstract	Recent studies in image retrieval task have shown that ensembling different models and combining multiple global descriptors lead to performance improvement. However, training different models for the ensemble is not only difficult but also inefficient with respect to time and memory. In this paper, we propose a novel framework that exploits multiple global descriptors to get an ensemble effect while it can be trained in an end-to-end manner. The proposed framework is flexible and expandable by the global descriptor, CNN backbone, loss, and dataset. Moreover, we investigate the effectiveness of combining multiple global descriptors with quantitative and qualitative analysis. Our extensive experiments show that the combined descriptor outperforms a single global descriptor, as it can utilize different types of feature properties. In the benchmark evaluation, the proposed framework achieves the state-of-the-art performance on the CARS196, CUB200-2011, In-shop Clothes, and Stanford Online Products on image retrieval tasks. Our model implementations and pretrained models are publicly available.
Tasks	Image Retrieval
Published	2019-03-26
URL	https://arxiv.org/abs/1903.10663v3
PDF	https://arxiv.org/pdf/1903.10663v3.pdf
PWC	https://paperswithcode.com/paper/combination-of-multiple-global-descriptors
Repo	https://github.com/naver/cgd
Framework	mxnet

Testing Robustness Against Unforeseen Adversaries


Title	Testing Robustness Against Unforeseen Adversaries
Authors	Daniel Kang, Yi Sun, Dan Hendrycks, Tom Brown, Jacob Steinhardt
Abstract	Considerable work on adversarial defense has studied robustness to a fixed, known family of adversarial distortions, most frequently L_p-bounded distortions. In reality, the specific form of attack will rarely be known and adversaries are free to employ distortions outside of any fixed set. The present work advocates measuring robustness against this much broader range of unforeseen attacks—attacks whose precise form is not known when designing a defense. We propose a methodology for evaluating a defense against a diverse range of distortion types together with a summary metric UAR that measures the Unforeseen Attack Robustness against a distortion. We construct novel JPEG, Fog, Gabor, and Snow adversarial attacks to simulate unforeseen adversaries and perform a careful study of adversarial robustness against these and existing distortion types. We find that evaluation against existing L_p attacks yields highly correlated information that may not generalize to other attacks and identify a set of 4 attacks that yields more diverse information. We further find that adversarial training against either one or multiple distortions, including our novel ones, does not confer robustness to unforeseen distortions. These results underscore the need to study robustness against unforeseen distortions and provide a starting point for doing so.
Tasks	Adversarial Defense
Published	2019-08-21
URL	https://arxiv.org/abs/1908.08016v1
PDF	https://arxiv.org/pdf/1908.08016v1.pdf
PWC	https://paperswithcode.com/paper/190808016
Repo	https://github.com/ddkang/advex-uar
Framework	pytorch

A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection


Title	A Tweet Dataset Annotated for Named Entity Recognition and Stance Detection
Authors	Dilek Küçük, Fazli Can
Abstract	Annotated datasets in different domains are critical for many supervised learning-based solutions to related problems and for the evaluation of the proposed solutions. Topics in natural language processing (NLP) similarly require annotated datasets to be used for such purposes. In this paper, we target at two NLP problems, named entity recognition and stance detection, and present the details of a tweet dataset in Turkish annotated for named entity and stance information. Within the course of the current study, both the named entity and stance annotations of the included tweets are made publicly available, although previously the dataset has been publicly shared with stance annotations only. We believe that this dataset will be useful for uncovering the possible relationships between named entity recognition and stance detection in tweets.
Tasks	Named Entity Recognition, Stance Detection
Published	2019-01-15
URL	http://arxiv.org/abs/1901.04787v2
PDF	http://arxiv.org/pdf/1901.04787v2.pdf
PWC	https://paperswithcode.com/paper/a-tweet-dataset-annotated-for-named-entity
Repo	https://github.com/dkucuk/Tweet-Dataset-NER-SD
Framework	none

Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians


Title	Modelling heterogeneous distributions with an Uncountable Mixture of Asymmetric Laplacians
Authors	Axel Brando, Jose A. Rodríguez-Serrano, Jordi Vitrià, Alberto Rubio
Abstract	In regression tasks, aleatoric uncertainty is commonly addressed by considering a parametric distribution of the output variable, which is based on strong assumptions such as symmetry, unimodality or by supposing a restricted shape. These assumptions are too limited in scenarios where complex shapes, strong skews or multiple modes are present. In this paper, we propose a generic deep learning framework that learns an Uncountable Mixture of Asymmetric Laplacians (UMAL), which will allow us to estimate heterogeneous distributions of the output variable and shows its connections to quantile regression. Despite having a fixed number of parameters, the model can be interpreted as an infinite mixture of components, which yields a flexible approximation for heterogeneous distributions. Apart from synthetic cases, we apply this model to room price forecasting and to predict financial operations in personal bank accounts. We demonstrate that UMAL produces proper distributions, which allows us to extract richer insights and to sharpen decision-making.
Tasks	Decision Making
Published	2019-10-27
URL	https://arxiv.org/abs/1910.12288v2
PDF	https://arxiv.org/pdf/1910.12288v2.pdf
PWC	https://paperswithcode.com/paper/modelling-heterogeneous-distributions-with-an
Repo	https://github.com/BBVA/UMAL
Framework	tf

Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks


Title	Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks
Authors	Aamir Mustafa, Salman Khan, Munawar Hayat, Roland Goecke, Jianbing Shen, Ling Shao
Abstract	Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images. The robustness of existing defenses suffers greatly under white-box attack settings, where an adversary has full knowledge about the network and can iterate several times to find strong perturbations. We observe that the main reason for the existence of such perturbations is the close proximity of different class samples in the learned feature space. This allows model decisions to be totally changed by adding an imperceptible perturbation in the inputs. To counter this, we propose to class-wise disentangle the intermediate feature representations of deep networks. Specifically, we force the features for each class to lie inside a convex polytope that is maximally separated from the polytopes of other classes. In this manner, the network is forced to learn distinct and distant decision regions for each class. We observe that this simple constraint on the features greatly enhances the robustness of learned models, even against the strongest white-box attacks, without degrading the classification performance on clean images. We report extensive evaluations in both black-box and white-box attack scenarios and show significant gains in comparison to state-of-the art defenses.
Tasks	Adversarial Defense
Published	2019-04-01
URL	https://arxiv.org/abs/1904.00887v4
PDF	https://arxiv.org/pdf/1904.00887v4.pdf
PWC	https://paperswithcode.com/paper/adversarial-defense-by-restricting-the-hidden
Repo	https://github.com/aamir-mustafa/pcl-adversarial-defense
Framework	pytorch

BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis


Title	BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis
Authors	Hu Xu, Bing Liu, Lei Shu, Philip S. Yu
Abstract	Question-answering plays an important role in e-commerce as it allows potential customers to actively seek crucial information about products or services to help their purchase decision making. Inspired by the recent success of machine reading comprehension (MRC) on formal documents, this paper explores the potential of turning customer reviews into a large source of knowledge that can be exploited to answer user questions.~We call this problem Review Reading Comprehension (RRC). To the best of our knowledge, no existing work has been done on RRC. In this work, we first build an RRC dataset called ReviewRC based on a popular benchmark for aspect-based sentiment analysis. Since ReviewRC has limited training examples for RRC (and also for aspect-based sentiment analysis), we then explore a novel post-training approach on the popular language model BERT to enhance the performance of fine-tuning of BERT for RRC. To show the generality of the approach, the proposed post-training is also applied to some other review-based tasks such as aspect extraction and aspect sentiment classification in aspect-based sentiment analysis. Experimental results demonstrate that the proposed post-training is highly effective. The datasets and code are available at https://www.cs.uic.edu/~hxu/.
Tasks	Aspect-Based Sentiment Analysis, Aspect Extraction, Reading Comprehension
Published	2019-04-03
URL	https://arxiv.org/abs/1904.02232v2
PDF	https://arxiv.org/pdf/1904.02232v2.pdf
PWC	https://paperswithcode.com/paper/bert-post-training-for-review-reading
Repo	https://github.com/howardhsu/BERT-for-RRC-ABSA
Framework	pytorch

Deep Text Mining of Instagram Data Without Strong Supervision


Title	Deep Text Mining of Instagram Data Without Strong Supervision
Authors	Kim Hammar, Shatha Jaradat, Nima Dokoohaki, Mihhail Matskin
Abstract	With the advent of social media, our online feeds increasingly consist of short, informal, and unstructured text. This textual data can be analyzed for the purpose of improving user recommendations and detecting trends. Instagram is one of the largest social media platforms, containing both text and images. However, most of the prior research on text processing in social media is focused on analyzing Twitter data, and little attention has been paid to text mining of Instagram data. Moreover, many text mining methods rely on annotated training data, which in practice is both difficult and expensive to obtain. In this paper, we present methods for unsupervised mining of fashion attributes from Instagram text, which can enable a new kind of user recommendation in the fashion domain. In this context, we analyze a corpora of Instagram posts from the fashion domain, introduce a system for extracting fashion attributes from Instagram, and train a deep clothing classifier with weak supervision to classify Instagram posts based on the associated text. With our experiments, we confirm that word embeddings are a useful asset for information extraction. Experimental results show that information extraction using word embeddings outperforms a baseline that uses Levenshtein distance. The results also show the benefit of combining weak supervision signals using generative models instead of majority voting. Using weak supervision and generative modeling, an F1 score of 0.61 is achieved on the task of classifying the image contents of Instagram posts based solely on the associated text, which is on level with human performance. Finally, our empirical study provides one of the few available studies on Instagram text and shows that the text is noisy, that the text distribution exhibits the long-tail phenomenon, and that comment sections on Instagram are multi-lingual.
Tasks	Word Embeddings
Published	2019-09-24
URL	https://arxiv.org/abs/1909.10812v1
PDF	https://arxiv.org/pdf/1909.10812v1.pdf
PWC	https://paperswithcode.com/paper/deep-text-mining-of-instagram-data-without
Repo	https://github.com/shatha2014/FashionRec
Framework	none

Correcting Predictions for Approximate Bayesian Inference


Title	Correcting Predictions for Approximate Bayesian Inference
Authors	Tomasz Kuśmierczyk, Joseph Sakaya, Arto Klami
Abstract	Bayesian models quantify uncertainty and facilitate optimal decision-making in downstream applications. For most models, however, practitioners are forced to use approximate inference techniques that lead to sub-optimal decisions due to incorrect posterior predictive distributions. We present a novel approach that corrects for inaccuracies in posterior inference by altering the decision-making process. We train a separate model to make optimal decisions under the approximate posterior, combining interpretable Bayesian modeling with optimization of direct predictive accuracy in a principled fashion. The solution is generally applicable as a plug-in module for predictive decision-making for arbitrary probabilistic programs, irrespective of the posterior inference strategy. We demonstrate the approach empirically in several problems, confirming its potential.
Tasks	Bayesian Inference, Decision Making
Published	2019-09-11
URL	https://arxiv.org/abs/1909.04919v1
PDF	https://arxiv.org/pdf/1909.04919v1.pdf
PWC	https://paperswithcode.com/paper/correcting-predictions-for-approximate
Repo	https://github.com/tkusmierczyk/correcting_approximate_bayesian_predictions
Framework	pytorch

MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity


Title	MonaLog: a Lightweight System for Natural Language Inference Based on Monotonicity
Authors	Hai Hu, Qi Chen, Kyle Richardson, Atreyee Mukherjee, Lawrence S. Moss, Sandra Kuebler
Abstract	We present a new logic-based inference engine for natural language inference (NLI) called MonaLog, which is based on natural logic and the monotonicity calculus. In contrast to existing logic-based approaches, our system is intentionally designed to be as lightweight as possible, and operates using a small set of well-known (surface-level) monotonicity facts about quantifiers, lexical items and tokenlevel polarity information. Despite its simplicity, we find our approach to be competitive with other logic-based NLI models on the SICK benchmark. We also use MonaLog in combination with the current state-of-the-art model BERT in a variety of settings, including for compositional data augmentation. We show that MonaLog is capable of generating large amounts of high-quality training data for BERT, improving its accuracy on SICK.
Tasks	Data Augmentation, Natural Language Inference
Published	2019-10-19
URL	https://arxiv.org/abs/1910.08772v1
PDF	https://arxiv.org/pdf/1910.08772v1.pdf
PWC	https://paperswithcode.com/paper/monalog-a-lightweight-system-for-natural
Repo	https://github.com/huhailinguist/ccg2mono
Framework	none

A Semi-Supervised Self-Organizing Map for Clustering and Classification


Title	A Semi-Supervised Self-Organizing Map for Clustering and Classification
Authors	Pedro H. M. Braga, Hansenclever F. Bassani
Abstract	There has been an increasing interest in semi-supervised learning in the recent years because of the great number of datasets with a large number of unlabeled data but only a few labeled samples. Semi-supervised learning algorithms can work with both types of data, combining them to obtain better performance for both clustering and classification. Also, these datasets commonly have a high number of dimensions. This article presents a new semi-supervised method based on self-organizing maps (SOMs) for clustering and classification, called Semi-Supervised Self-Organizing Map (SS-SOM). The method can dynamically switch between supervised and unsupervised learning during the training according to the availability of the class labels for each pattern. Our results show that the SS-SOM outperforms other semi-supervised methods in conditions in which there is a low amount of labeled samples, also achieving good results when all samples are labeled.
Tasks
Published	2019-07-01
URL	https://arxiv.org/abs/1907.01070v1
PDF	https://arxiv.org/pdf/1907.01070v1.pdf
PWC	https://paperswithcode.com/paper/a-semi-supervised-self-organizing-map-for
Repo	https://github.com/phbraga/SS-SOM
Framework	none

EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural Annotators


Title	EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural Annotators
Authors	Chandrakant Bothe, Cornelius Weber, Sven Magg, Stefan Wermter
Abstract	The recognition of emotion and dialogue acts enriches conversational analysis and help to build natural dialogue systems. Emotion interpretation makes us understand feelings and dialogue acts reflect the intentions and performative functions in the utterances. However, most of the textual and multi-modal conversational emotion corpora contain only emotion labels but not dialogue acts. To address this problem, we propose to use a pool of various recurrent neural models trained on a dialogue act corpus, with and without context. These neural models annotate the emotion corpora with dialogue act labels, and an ensemble annotator extracts the final dialogue act label. We annotated two accessible multi-modal emotion corpora: IEMOCAP and MELD. We analyzed the co-occurrence of emotion and dialogue act labels and discovered specific relations. For example, Accept/Agree dialogue acts often occur with the Joy emotion, Apology with Sadness, and Thanking with Joy. We make the Emotional Dialogue Acts (EDA) corpus publicly available to the research community for further study and analysis.
Tasks
Published	2019-12-02
URL	https://arxiv.org/abs/1912.00819v3
PDF	https://arxiv.org/pdf/1912.00819v3.pdf
PWC	https://paperswithcode.com/paper/enriching-existing-conversational-emotion
Repo	https://github.com/bothe/EDAs
Framework	none

Robustness Verification of Tree-based Models


Title	Robustness Verification of Tree-based Models
Authors	Hongge Chen, Huan Zhang, Si Si, Yang Li, Duane Boning, Cho-Jui Hsieh
Abstract	We study the robustness verification problem for tree-based models, including decision trees, random forests (RFs) and gradient boosted decision trees (GBDTs). Formal robustness verification of decision tree ensembles involves finding the exact minimal adversarial perturbation or a guaranteed lower bound of it. Existing approaches find the minimal adversarial perturbation by a mixed integer linear programming (MILP) problem, which takes exponential time so is impractical for large ensembles. Although this verification problem is NP-complete in general, we give a more precise complexity characterization. We show that there is a simple linear time algorithm for verifying a single tree, and for tree ensembles, the verification problem can be cast as a max-clique problem on a multi-partite graph with bounded boxicity. For low dimensional problems when boxicity can be viewed as constant, this reformulation leads to a polynomial time algorithm. For general problems, by exploiting the boxicity of the graph, we develop an efficient multi-level verification algorithm that can give tight lower bounds on the robustness of decision tree ensembles, while allowing iterative improvement and any-time termination. OnRF/GBDT models trained on 10 datasets, our algorithm is hundreds of times faster than the previous approach that requires solving MILPs, and is able to give tight robustness verification bounds on large GBDTs with hundreds of deep trees.
Tasks
Published	2019-06-10
URL	https://arxiv.org/abs/1906.03849v3
PDF	https://arxiv.org/pdf/1906.03849v3.pdf
PWC	https://paperswithcode.com/paper/robustness-verification-of-tree-based-models
Repo	https://github.com/chenhongge/treeVerification
Framework	none

Learning higher-order logic programs


Title	Learning higher-order logic programs
Authors	Andrew Cropper, Rolf Morel, Stephen H. Muggleton
Abstract	A key feature of inductive logic programming (ILP) is its ability to learn first-order programs, which are intrinsically more expressive than propositional programs. In this paper, we introduce techniques to learn higher-order programs. Specifically, we extend meta-interpretive learning (MIL) to support learning higher-order programs by allowing for \emph{higher-order definitions} to be used as background knowledge. Our theoretical results show that learning higher-order programs, rather than first-order programs, can reduce the textual complexity required to express programs which in turn reduces the size of the hypothesis space and sample complexity. We implement our idea in two new MIL systems: the Prolog system \namea{} and the ASP system \nameb{}. Both systems support learning higher-order programs and higher-order predicate invention, such as inventing functions for \tw{map/3} and conditions for \tw{filter/3}. We conduct experiments on four domains (robot strategies, chess playing, list transformations, and string decryption) that compare learning first-order and higher-order programs. Our experimental results support our theoretical claims and show that, compared to learning first-order programs, learning higher-order programs can significantly improve predictive accuracies and reduce learning times.
Tasks
Published	2019-07-25
URL	https://arxiv.org/abs/1907.10953v1
PDF	https://arxiv.org/pdf/1907.10953v1.pdf
PWC	https://paperswithcode.com/paper/learning-higher-order-logic-programs
Repo	https://github.com/metagol/metagol
Framework	none

Student Engagement Detection Using Emotion Analysis, Eye Tracking and Head Movement with Machine Learning


Title	Student Engagement Detection Using Emotion Analysis, Eye Tracking and Head Movement with Machine Learning
Authors	Prabin Sharma, Shubham Joshi, Subash Gautam, Vitor Filipe, Manuel J. C. S. Reis
Abstract	With the increase of distance learning, in general, and e-learning, in particular, having a system capable of determining the engagement of students is of primordial importance, and one of the biggest challenges, both for teachers, researchers and policy makers. Here, we present a system to detect the engagement level of the students. It uses only information provided by the typical built-in web-camera present in a laptop computer, and was designed to work in real time. We combine information about the movements of the eyes and head, and facial emotions to produce a concentration index with three classes of engagement: “very engaged”, “nominally engaged” and “not engaged at all”. The system was tested in a typical e-learning scenario, and the results show that it correctly identifies each period of time where students were “very engaged”, “nominally engaged” and “not engaged at all”. Additionally, the results also show that the students with best scores also have higher concentration indexes.
Tasks	Emotion Recognition, Eye Tracking
Published	2019-09-18
URL	https://arxiv.org/abs/1909.12913v2
PDF	https://arxiv.org/pdf/1909.12913v2.pdf
PWC	https://paperswithcode.com/paper/student-engagement-detection-using-emotion
Repo	https://github.com/CaedenZ/distractionModel
Framework	none

AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations


Title	AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
Authors	Xiao Zhang, Rui Zhao, Yu Qiao, Xiaogang Wang, Hongsheng Li
Abstract	The cosine-based softmax losses and their variants achieve great success in deep learning based face recognition. However, hyperparameter settings in these losses have significant influences on the optimization path as well as the final recognition performance. Manually tuning those hyperparameters heavily relies on user experience and requires many training tricks. In this paper, we investigate in depth the effects of two important hyperparameters of cosine-based softmax losses, the scale parameter and angular margin parameter, by analyzing how they modulate the predicted classification probability. Based on these analysis, we propose a novel cosine-based softmax loss, AdaCos, which is hyperparameter-free and leverages an adaptive scale parameter to automatically strengthen the training supervisions during the training process. We apply the proposed AdaCos loss to large-scale face verification and identification datasets, including LFW, MegaFace, and IJB-C 1:1 Verification. Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy. Our method outperforms state-of-the-art softmax losses on all the three datasets.
Tasks	Face Recognition, Face Verification
Published	2019-05-01
URL	https://arxiv.org/abs/1905.00292v2
PDF	https://arxiv.org/pdf/1905.00292v2.pdf
PWC	https://paperswithcode.com/paper/adacos-adaptively-scaling-cosine-logits-for
Repo	https://github.com/4uiiurz1/pytorch-adacos
Framework	pytorch