January 29, 2020

3270 words 16 mins read

Paper Group ANR 714

SADIH: Semantic-Aware DIscrete Hashing. Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?. Subjectivity and complexity of facial attractiveness. VAT tax gap prediction: a 2-steps Gradient Boosting approach. Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective. Targ …

SADIH: Semantic-Aware DIscrete Hashing


Title	SADIH: Semantic-Aware DIscrete Hashing
Authors	Zheng Zhang, Guo-sen Xie, Yang Li, Sheng Li, Zi Huang
Abstract	Due to its low storage cost and fast query speed, hashing has been recognized to accomplish similarity search in large-scale multimedia retrieval applications. Particularly supervised hashing has recently received considerable research attention by leveraging the label information to preserve the pairwise similarities of data points in the Hamming space. However, there still remain two crucial bottlenecks: 1) the learning process of the full pairwise similarity preservation is computationally unaffordable and unscalable to deal with big data; 2) the available category information of data are not well-explored to learn discriminative hash functions. To overcome these challenges, we propose a unified Semantic-Aware DIscrete Hashing (SADIH) framework, which aims to directly embed the transformed semantic information into the asymmetric similarity approximation and discriminative hashing function learning. Specifically, a semantic-aware latent embedding is introduced to asymmetrically preserve the full pairwise similarities while skillfully handle the cumbersome n times n pairwise similarity matrix. Meanwhile, a semantic-aware autoencoder is developed to jointly preserve the data structures in the discriminative latent semantic space and perform data reconstruction. Moreover, an efficient alternating optimization algorithm is proposed to solve the resulting discrete optimization problem. Extensive experimental results on multiple large-scale datasets demonstrate that our SADIH can clearly outperform the state-of-the-art baselines with the additional benefit of lower computational costs.
Tasks
Published	2019-04-03
URL	http://arxiv.org/abs/1904.01739v2
PDF	http://arxiv.org/pdf/1904.01739v2.pdf
PWC	https://paperswithcode.com/paper/sadih-semantic-aware-discrete-hashing
Repo
Framework

Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?


Title	Accuracy comparison across face recognition algorithms: Where are we on measuring race bias?
Authors	Jacqueline G. Cavazos, P. Jonathon Phillips, Carlos D. Castillo, Alice J. O’Toole
Abstract	Previous generations of face recognition algorithms differ in accuracy for faces of different races (race bias). Whether deep convolutional neural networks (DCNNs) are race biased is less studied. To measure race bias in algorithms, it is important to consider the underlying factors. Here, we present the possible underlying factors and methodological considerations for assessing race bias in algorithms. We investigate data-driven and scenario modeling factors. Data-driven factors include image quality, image population statistics, and algorithm architecture. Scenario modeling considers the role of the “user” of the algorithm (e.g., threshold decisions and demographic constraints). To illustrate how these issues apply, we present data from four face recognition algorithms (one pre- DCNN, three DCNN) for Asian and Caucasian faces. First, for all four algorithms, the degree of bias varied depending on the identification decision threshold. Second, for all algorithms, to achieve equal false accept rates (FARs), Asian faces required higher identification thresholds than Caucasian faces. Third, dataset difficulty affected both overall recognition accuracy and race bias. Fourth, demographic constraints on the formulation of the distributions used in the test, impacted estimates of algorithm accuracy. We conclude with a recommended checklist for measuring race bias in face recognition algorithms.
Tasks	Face Recognition
Published	2019-12-16
URL	https://arxiv.org/abs/1912.07398v1
PDF	https://arxiv.org/pdf/1912.07398v1.pdf
PWC	https://paperswithcode.com/paper/accuracy-comparison-across-face-recognition
Repo
Framework

Subjectivity and complexity of facial attractiveness


Title	Subjectivity and complexity of facial attractiveness
Authors	Miguel Ibáñez-Berganza, Ambra Amico, Vittorio Loreto
Abstract	The origin and meaning of facial beauty represent a longstanding puzzle. Despite the profuse literature devoted to facial attractiveness, its very nature, its determinants and the nature of inter-person differences remain controversial issues. Here we tackle such questions proposing a novel experimental approach in which human subjects, instead of rating natural faces, are allowed to efficiently explore the face-space and ‘sculpt’ their favorite variation of a reference facial image. The results reveal that different subjects prefer distinguishable regions of the face-space, highlighting the essential subjectivity of the phenomenon.The different sculpted facial vectors exhibit strong correlations among pairs of facial distances, characterising the underlying universality and complexity of the cognitive processes, and the relative relevance and robustness of the different facial distances.
Tasks
Published	2019-03-18
URL	https://arxiv.org/abs/1903.07526v2
PDF	https://arxiv.org/pdf/1903.07526v2.pdf
PWC	https://paperswithcode.com/paper/subjectivity-and-complexity-of-facial
Repo
Framework

VAT tax gap prediction: a 2-steps Gradient Boosting approach


Title	VAT tax gap prediction: a 2-steps Gradient Boosting approach
Authors	Giovanna Tagliaferri, Daria Scacciatelli, Pierfrancesco Alaimo Di Loro
Abstract	Tax evasion is the illegal non-payment of taxes by individuals, corporations, and trusts. It results in a loss of state revenue that can undermine the effectiveness of government policies. One measure of tax evasion is the so-called tax gap: the difference between the income that should be reported to the tax authorities and the amount actually reported. However, economists lack a robust method for estimating the tax gap through a bottom-up approach based on fiscal audits. This is difficult because the declared tax base is available on the whole population but the income reported to the tax authorities is generally available only on a small, non-random sample of audited units. This induces a selection bias which invalidates standard statistical methods. Here, we use machine learning based on a 2-steps Gradient Boosting model, to correct for the selection bias without requiring any strong assumption on the distribution. We use our method to estimate the Italian VAT Gap related to individual firms based on information gathered from administrative sources. Our algorithm estimates the potential VAT turnover of Italian individual firms for the fiscal year 2011 and suggests that the tax gap is about 30% of the total potential tax base. Comparisons with other methods show our technique offers a significant improvement in predictive performance.
Tasks
Published	2019-12-08
URL	https://arxiv.org/abs/1912.03781v1
PDF	https://arxiv.org/pdf/1912.03781v1.pdf
PWC	https://paperswithcode.com/paper/vat-tax-gap-prediction-a-2-steps-gradient
Repo
Framework

Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective


Title	Visual-based Autonomous Driving Deployment from a Stochastic and Uncertainty-aware Perspective
Authors	Lei Tai, Peng Yun, Yuying Chen, Congcong Liu, Haoyang Ye, Ming Liu
Abstract	End-to-end visual-based imitation learning has been widely applied in autonomous driving. When deploying the trained visual-based driving policy, a deterministic command is usually directly applied without considering the uncertainty of the input data. Such kind of policies may bring dramatical damage when applied in the real world. In this paper, we follow the recent real-to-sim pipeline by translating the testing world image back to the training domain when using the trained policy. In the translating process, a stochastic generator is used to generate various images stylized under the training domain randomly or directionally. Based on those translated images, the trained uncertainty-aware imitation learning policy would output both the predicted action and the data uncertainty motivated by the aleatoric loss function. Through the uncertainty-aware imitation learning policy, we can easily choose the safest one with the lowest uncertainty among the generated images. Experiments in the Carla navigation benchmark show that our strategy outperforms previous methods, especially in dynamic environments.
Tasks	Autonomous Driving, Domain Adaptation, Imitation Learning
Published	2019-03-03
URL	https://arxiv.org/abs/1903.00821v2
PDF	https://arxiv.org/pdf/1903.00821v2.pdf
PWC	https://paperswithcode.com/paper/end-to-end-driving-deploying-through
Repo
Framework

Target-based Hyperspectral Demixing via Generalized Robust PCA


Title	Target-based Hyperspectral Demixing via Generalized Robust PCA
Authors	Sirisha Rambhatla, Xingguo Li, Jarvis Haupt
Abstract	Localizing targets of interest in a given hyperspectral (HS) image has applications ranging from remote sensing to surveillance. This task of target detection leverages the fact that each material/object possesses its own characteristic spectral response, depending upon its composition. As $\textit{signatures}$ of different materials are often correlated, matched filtering based approaches may not be appropriate in this case. In this work, we present a technique to localize targets of interest based on their spectral signatures. We also present the corresponding recovery guarantees, leveraging our recent theoretical results. To this end, we model a HS image as a superposition of a low-rank component and a dictionary sparse component, wherein the dictionary consists of the $\textit{a priori}$ known characteristic spectral responses of the target we wish to localize. Finally, we analyze the performance of the proposed approach via experimental validation on real HS data for a classification task, and compare it with related techniques.
Tasks
Published	2019-02-26
URL	http://arxiv.org/abs/1902.11111v1
PDF	http://arxiv.org/pdf/1902.11111v1.pdf
PWC	https://paperswithcode.com/paper/target-based-hyperspectral-demixing-via
Repo
Framework

Variational approximations using Fisher divergence


Title	Variational approximations using Fisher divergence
Authors	Yue Yang, Ryan Martin, Howard Bondell
Abstract	Modern applications of Bayesian inference involve models that are sufficiently complex that the corresponding posterior distributions are intractable and must be approximated. The most common approximation is based on Markov chain Monte Carlo, but these can be expensive when the data set is large and/or the model is complex, so more efficient variational approximations have recently received considerable attention. The traditional variational methods, that seek to minimize the Kullback–Leibler divergence between the posterior and a relatively simple parametric family, provide accurate and efficient estimation of the posterior mean, but often does not capture other moments, and have limitations in terms of the models to which they can be applied. Here we propose the construction of variational approximations based on minimizing the Fisher divergence, and develop an efficient computational algorithm that can be applied to a wide range of models without conjugacy or potentially unrealistic mean-field assumptions. We demonstrate the superior performance of the proposed method for the benchmark case of logistic regression.
Tasks	Bayesian Inference
Published	2019-05-13
URL	https://arxiv.org/abs/1905.05284v1
PDF	https://arxiv.org/pdf/1905.05284v1.pdf
PWC	https://paperswithcode.com/paper/variational-approximations-using-fisher
Repo
Framework

Why ADAM Beats SGD for Attention Models


Title	Why ADAM Beats SGD for Attention Models
Authors	Jingzhao Zhang, Sai Praneeth Karimireddy, Andreas Veit, Seungyeon Kim, Sashank J Reddi, Sanjiv Kumar, Suvrit Sra
Abstract	While stochastic gradient descent (SGD) is still the de facto algorithm in deep learning, adaptive methods like Adam have been observed to outperform SGD across important tasks, such as attention models. The settings under which SGD performs poorly in comparison to Adam are not well understood yet. In this paper, we provide empirical and theoretical evidence that a heavy-tailed distribution of the noise in stochastic gradients is a root cause of SGD’s poor performance. Based on this observation, we study clipped variants of SGD that circumvent this issue; we then analyze their convergence under heavy-tailed noise. Furthermore, we develop a new adaptive coordinate-wise clipping algorithm (ACClip) tailored to such settings. Subsequently, we show how adaptive methods like Adam can be viewed through the lens of clipping, which helps us explain Adam’s strong performance under heavy-tail noise settings. Finally, we show that the proposed ACClip outperforms Adam for both BERT pretraining and finetuning tasks.
Tasks
Published	2019-12-06
URL	https://arxiv.org/abs/1912.03194v1
PDF	https://arxiv.org/pdf/1912.03194v1.pdf
PWC	https://paperswithcode.com/paper/why-adam-beats-sgd-for-attention-models-1
Repo
Framework

Efficient Bidirectional Neural Machine Translation


Title	Efficient Bidirectional Neural Machine Translation
Authors	Xu Tan, Yingce Xia, Lijun Wu, Tao Qin
Abstract	The encoder-decoder based neural machine translation usually generates a target sequence token by token from left to right. Due to error propagation, the tokens in the right side of the generated sequence are usually of poorer quality than those in the left side. In this paper, we propose an efficient method to generate a sequence in both left-to-right and right-to-left manners using a single encoder and decoder, combining the advantages of both generation directions. Experiments on three translation tasks show that our method achieves significant improvements over conventional unidirectional approach. Compared with ensemble methods that train and combine two models with different generation directions, our method saves 50% model parameters and about 40% training time, and also improve inference speed.
Tasks	Machine Translation
Published	2019-08-25
URL	https://arxiv.org/abs/1908.09329v1
PDF	https://arxiv.org/pdf/1908.09329v1.pdf
PWC	https://paperswithcode.com/paper/efficient-bidirectional-neural-machine
Repo
Framework

Global Voices: Crossing Borders in Automatic News Summarization


Title	Global Voices: Crossing Borders in Automatic News Summarization
Authors	Khanh Nguyen, Hal Daumé III
Abstract	We construct Global Voices, a multilingual dataset for evaluating cross-lingual summarization methods. We extract social-network descriptions of Global Voices news articles to cheaply collect evaluation data for into-English and from-English summarization in 15 languages. Especially, for the into-English summarization task, we crowd-source a high-quality evaluation dataset based on guidelines that emphasize accuracy, coverage, and understandability. To ensure the quality of this dataset, we collect human ratings to filter out bad summaries, and conduct a survey on humans, which shows that the remaining summaries are preferred over the social-network summaries. We study the effect of translation quality in cross-lingual summarization, comparing a translate-then-summarize approach with several baselines. Our results highlight the limitations of the ROUGE metric that are overlooked in monolingual summarization.
Tasks
Published	2019-10-01
URL	https://arxiv.org/abs/1910.00421v3
PDF	https://arxiv.org/pdf/1910.00421v3.pdf
PWC	https://paperswithcode.com/paper/global-voices-crossing-borders-in-automatic
Repo
Framework

A Simple Heuristic for Bayesian Optimization with A Low Budget


Title	A Simple Heuristic for Bayesian Optimization with A Low Budget
Authors	Masahiro Nomura, Kenshi Abe
Abstract	The aim of black-box optimization is to optimize an objective function within the constraints of a given evaluation budget. In this problem, it is generally assumed that the computational cost for evaluating a point is large; thus, it is important to search efficiently with as low budget as possible. Bayesian optimization is an efficient method for black-box optimization and provides exploration-exploitation trade-off by constructing a surrogate model that considers uncertainty of the objective function. However, because Bayesian optimization should construct the surrogate model for the entire search space, it does not exhibit good performance when points are not sampled sufficiently. In this study, we develop a heuristic method refining the search space for Bayesian optimization when the available evaluation budget is low. The proposed method refines a promising region by dividing the original region so that Bayesian optimization can be executed with the promising region as the initial search space. We confirm that Bayesian optimization with the proposed method outperforms Bayesian optimization alone and shows equal or better performance to two search-space division algorithms through experiments on the benchmark functions and the hyperparameter optimization of machine learning algorithms.
Tasks	Hyperparameter Optimization
Published	2019-11-18
URL	https://arxiv.org/abs/1911.07790v3
PDF	https://arxiv.org/pdf/1911.07790v3.pdf
PWC	https://paperswithcode.com/paper/a-simple-heuristic-for-bayesian-optimization
Repo
Framework


Title	A Neural Network Based on the Johnson $S_\mathrm{U}$ Translation System and Related Application to Electromyogram Classification
Authors	Hideaki Hayashi, Taro Shibanoki, Toshio Tsuji
Abstract	Electromyogram (EMG) classification is a key technique in EMG-based control systems. The existing EMG classification methods do not consider the characteristics of EMG features that the distribution has skewness and kurtosis, causing drawbacks such as the requirement of hyperparameter tuning. In this paper, we propose a neural network based on the Johnson $S_\mathrm{U}$ translation system that is capable of representing distributions with skewness and kurtosis. The Johnson system is a normalizing translation that transforms non-normal data to a normal distribution, thereby enabling the representation of a wide range of distributions. In this study, a discriminative model based on the multivariate Johnson $S_\mathrm{U}$ translation system is transformed into a linear combination of coefficients and input vectors using log-linearization. This is then incorporated into a neural network structure, thereby allowing the calculation of the posterior probability of the input vectors for each class and the determination of model parameters as weight coefficients of the network. The uniqueness of convergence of the network learning is theoretically guaranteed. In the experiments, the suitability of the proposed network for distributions including skewness and kurtosis is evaluated using artificially generated data. Its applicability for real biological data is also evaluated via an EMG classification experiment. The results show that the proposed network achieves high classification performance without the need for hyperparameter optimization.
Tasks	Hyperparameter Optimization
Published	2019-11-14
URL	https://arxiv.org/abs/1912.04218v1
PDF	https://arxiv.org/pdf/1912.04218v1.pdf
PWC	https://paperswithcode.com/paper/a-neural-network-based-on-the-johnson
Repo
Framework

A Federated Learning Approach for Mobile Packet Classification


Title	A Federated Learning Approach for Mobile Packet Classification
Authors	Evita Bakopoulou, Balint Tillman, Athina Markopoulou
Abstract	In order to improve mobile data transparency, a number of network-based approaches have been proposed to inspect packets generated by mobile devices and detect personally identifiable information (PII), ad requests, or other activities. State-of-the-art approaches train classifiers based on features extracted from HTTP packets. So far, these classifiers have only been trained in a centralized way, where mobile users label and upload their packet logs to a central server, which then trains a global classifier and shares it with the users to apply on their devices. However, packet logs used as training data may contain sensitive information that users may not want to share/upload. In this paper, we apply, for the first time, a Federated Learning approach to mobile packet classification, which allows mobile devices to collaborate and train a global model, without sharing raw training data. Methodological challenges we address in this context include: model and feature selection, and tuning the Federated Learning parameters. We apply our framework to two different packet classification tasks (i.e., to predict PII exposure or ad requests in HTTP packets) and we demonstrate its effectiveness in terms of classification performance, communication and computation cost, using three real-world datasets.
Tasks	Feature Selection
Published	2019-07-30
URL	https://arxiv.org/abs/1907.13113v1
PDF	https://arxiv.org/pdf/1907.13113v1.pdf
PWC	https://paperswithcode.com/paper/a-federated-learning-approach-for-mobile
Repo
Framework

FDive: Learning Relevance Models using Pattern-based Similarity Measures


Title	FDive: Learning Relevance Models using Pattern-based Similarity Measures
Authors	Frederik L. Dennig, Tom Polk, Zudi Lin, Tobias Schreck, Hanspeter Pfister, Michael Behrisch
Abstract	The detection of interesting patterns in large high-dimensional datasets is difficult because of their dimensionality and pattern complexity. Therefore, analysts require automated support for the extraction of relevant patterns. In this paper, we present FDive, a visual active learning system that helps to create visually explorable relevance models, assisted by learning a pattern-based similarity. We use a small set of user-provided labels to rank similarity measures, consisting of feature descriptor and distance function combinations, by their ability to distinguish relevant from irrelevant data. Based on the best-ranked similarity measure, the system calculates an interactive Self-Organizing Map-based relevance model, which classifies data according to the cluster affiliation. It also automatically prompts further relevance feedback to improve its accuracy. Uncertain areas, especially near the decision boundaries, are highlighted and can be refined by the user. We evaluate our approach by comparison to state-of-the-art feature selection techniques and demonstrate the usefulness of our approach by a case study classifying electron microscopy images of brain cells. The results show that FDive enhances both the quality and understanding of relevance models and can thus lead to new insights for brain research.
Tasks	Active Learning, Feature Selection
Published	2019-07-29
URL	https://arxiv.org/abs/1907.12489v2
PDF	https://arxiv.org/pdf/1907.12489v2.pdf
PWC	https://paperswithcode.com/paper/fdive-learning-relevance-models-using-pattern
Repo
Framework

Generating Persuasive Visual Storylines for Promotional Videos


Title	Generating Persuasive Visual Storylines for Promotional Videos
Authors	Chang Liu, Yi Dong, Han Yu, Zhiqi Shen, Zhanning Gao, Pan Wang, Changgong Zhang, Peiran Ren, Xuansong Xie, Lizhen Cui, Chunyan Miao
Abstract	Video contents have become a critical tool for promoting products in E-commerce. However, the lack of automatic promotional video generation solutions makes large-scale video-based promotion campaigns infeasible. The first step of automatically producing promotional videos is to generate visual storylines, which is to select the building block footage and place them in an appropriate order. This task is related to the subjective viewing experience. It is hitherto performed by human experts and thus, hard to scale. To address this problem, we propose WundtBackpack, an algorithmic approach to generate storylines based on available visual materials, which can be video clips or images. It consists of two main parts, 1) the Learnable Wundt Curve to evaluate the perceived persuasiveness based on the stimulus intensity of a sequence of visual materials, which only requires a small volume of data to train; and 2) a clustering-based backpacking algorithm to generate persuasive sequences of visual materials while considering video length constraints. In this way, the proposed approach provides a dynamic structure to empower artificial intelligence (AI) to organize video footage in order to construct a sequence of visual stimuli with persuasive power. Extensive real-world experiments show that our approach achieves close to 10% higher perceived persuasiveness scores by human testers, and 12.5% higher expected revenue compared to the best performing state-of-the-art approach.
Tasks	Video Generation
Published	2019-08-30
URL	https://arxiv.org/abs/1908.11588v1
PDF	https://arxiv.org/pdf/1908.11588v1.pdf
PWC	https://paperswithcode.com/paper/generating-persuasive-visual-storylines-for
Repo
Framework