January 26, 2020

2911 words 14 mins read

Paper Group ANR 1402

Test-Time Training for Out-of-Distribution Generalization. Large-scale Tag-based Font Retrieval with Generative Feature Learning. Non-Bayesian Social Learning with Uncertain Models. Text Mining Customer Reviews For Aspect-based Restaurant Rating. Smooth Extrapolation of Unknown Anatomy via Statistical Shape Models. GAN-based Pose-aware Regulation f …

Test-Time Training for Out-of-Distribution Generalization


Title	Test-Time Training for Out-of-Distribution Generalization
Authors	Yu Sun, Xiaolong Wang, Zhuang Liu, John Miller, Alexei A. Efros, Moritz Hardt
Abstract	We introduce a general approach, called test-time training, for improving the performance of predictive models when test and training data come from different distributions. Test-time training turns a single unlabeled test instance into a self-supervised learning problem, on which we update the model parameters before making a prediction on this instance. We show that this simple idea leads to surprising improvements on diverse image classification benchmarks aimed at evaluating robustness to distribution shifts. Theoretical investigations on a convex model reveal helpful intuitions for when we can expect our approach to help.
Tasks	Image Classification
Published	2019-09-29
URL	https://arxiv.org/abs/1909.13231v2
PDF	https://arxiv.org/pdf/1909.13231v2.pdf
PWC	https://paperswithcode.com/paper/test-time-training-for-out-of-distribution-1
Repo
Framework

Large-scale Tag-based Font Retrieval with Generative Feature Learning


Title	Large-scale Tag-based Font Retrieval with Generative Feature Learning
Authors	Tianlang Chen, Zhaowen Wang, Ning Xu, Hailin Jin, Jiebo Luo
Abstract	Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag relations. We propose a novel generative feature learning algorithm that leverages the unique characteristics of fonts. The key idea is that font images are synthetic and can therefore be controlled by the learning algorithm. We design an integrated rendering and learning process so that the visual feature from one image can be used to reconstruct another image with different text. The resulting feature captures important font design details while is robust to nuisance factors such as text. We propose a novel attention mechanism to re-weight the visual feature for joint visual-text modeling. We combine the feature and the attention mechanism in a novel recognition-retrieval model. Experimental results show that our method significantly outperforms the state-of-the-art for the important problem of large-scale tag-based font retrieval.
Tasks
Published	2019-09-04
URL	https://arxiv.org/abs/1909.02072v2
PDF	https://arxiv.org/pdf/1909.02072v2.pdf
PWC	https://paperswithcode.com/paper/large-scale-tag-based-font-retrieval-with
Repo
Framework


Title	Non-Bayesian Social Learning with Uncertain Models
Authors	James Z. Hare, Cesar A. Uribe, Lance Kaplan, Ali Jadbabaie
Abstract	Non-Bayesian social learning theory provides a framework that models distributed inference for a group of agents interacting over a social network. In this framework, each agent iteratively forms and communicates beliefs about an unknown state of the world with their neighbors using a learning rule. Existing approaches assume agents have access to precise statistical models (in the form of likelihoods) for the state of the world. However in many situations, such models must be learned from finite data. We propose a social learning rule that takes into account uncertainty in the statistical models using second-order probabilities. Therefore, beliefs derived from uncertain models are sensitive to the amount of past evidence collected for each hypothesis. We characterize how well the hypotheses can be tested on a social network, as consistent or not with the state of the world. We explicitly show the dependency of the generated beliefs with respect to the amount of prior evidence. Moreover, as the amount of prior evidence goes to infinity, learning occurs and is consistent with traditional social learning theory.
Tasks
Published	2019-09-09
URL	https://arxiv.org/abs/1909.09228v2
PDF	https://arxiv.org/pdf/1909.09228v2.pdf
PWC	https://paperswithcode.com/paper/non-bayesian-social-learning-with-uncertain
Repo
Framework

Text Mining Customer Reviews For Aspect-based Restaurant Rating


Title	Text Mining Customer Reviews For Aspect-based Restaurant Rating
Authors	Jovelyn C. Cuizon, Jesserine Lopez, Danica Rose Jones
Abstract	This study applies text mining to analyze customer reviews and automatically assign a collective restaurant star rating based on five predetermined aspects: ambiance, cost, food, hygiene, and service. The application provides a web and mobile crowd sourcing platform where users share dining experiences and get insights about the strengths and weaknesses of a restaurant through user contributed feedback. Text reviews are tokenized into sentences. Noun-adjective pairs are extracted from each sentence using Stanford Core NLP library and are associated to aspects based on the bag of associated words fed into the system. The sentiment weight of the adjectives is determined through AFINN library. An overall restaurant star rating is computed based on the individual aspect rating. Further, a word cloud is generated to provide visual display of the most frequently occurring terms in the reviews. The more feedbacks are added the more reflective the sentiment score to the restaurants’ performance.
Tasks
Published	2019-01-07
URL	http://arxiv.org/abs/1901.01642v1
PDF	http://arxiv.org/pdf/1901.01642v1.pdf
PWC	https://paperswithcode.com/paper/text-mining-customer-reviews-for-aspect-based
Repo
Framework

Smooth Extrapolation of Unknown Anatomy via Statistical Shape Models


Title	Smooth Extrapolation of Unknown Anatomy via Statistical Shape Models
Authors	Robert Grupp, Hsin-Hong Chiang, Yoshito Otake, Ryan Murphy, Chad Gordon, Mehran Armand, Russell Taylor
Abstract	Several methods to perform extrapolation of unknown anatomy were evaluated. The primary application is to enhance surgical procedures that may use partial medical images or medical images of incomplete anatomy. Le Fort-based, face-jaw-teeth transplant is one such procedure. From CT data of 36 skulls and 21 mandibles separate Statistical Shape Models of the anatomical surfaces were created. Using the Statistical Shape Models, incomplete surfaces were projected to obtain complete surface estimates. The surface estimates exhibit non-zero error in regions where the true surface is known; it is desirable to keep the true surface and seamlessly merge the estimated unknown surface. Existing extrapolation techniques produce non-smooth transitions from the true surface to the estimated surface, resulting in additional error and a less aesthetically pleasing result. The three extrapolation techniques evaluated were: copying and pasting of the surface estimate (non-smooth baseline), a feathering between the patient surface and surface estimate, and an estimate generated via a Thin Plate Spline trained from displacements between the surface estimate and corresponding vertices of the known patient surface. Feathering and Thin Plate Spline approaches both yielded smooth transitions. However, feathering corrupted known vertex values. Leave-one-out analyses were conducted, with 5% to 50% of known anatomy removed from the left-out patient and estimated via the proposed approaches. The Thin Plate Spline approach yielded smaller errors than the other two approaches, with an average vertex error improvement of 1.46 mm and 1.38 mm for the skull and mandible respectively, over the baseline approach.
Tasks
Published	2019-09-23
URL	https://arxiv.org/abs/1909.10153v1
PDF	https://arxiv.org/pdf/1909.10153v1.pdf
PWC	https://paperswithcode.com/paper/190910153
Repo
Framework

GAN-based Pose-aware Regulation for Video-based Person Re-identification


Title	GAN-based Pose-aware Regulation for Video-based Person Re-identification
Authors	Alessandro Borgia, Yang Hua, Elyor Kodirov, Neil M. Robertson
Abstract	Video-based person re-identification deals with the inherent difficulty of matching unregulated sequences with different length and with incomplete target pose/viewpoint structure. Common approaches operate either by reducing the problem to the still images case, facing a significant information loss, or by exploiting inter-sequence temporal dependencies as in Siamese Recurrent Neural Networks or in gait analysis. However, in all cases, the inter-sequences pose/viewpoint misalignment is not considered, and the existing spatial approaches are mostly limited to the still images context. To this end, we propose a novel approach that can exploit more effectively the rich video information, by accounting for the role that the changing pose/viewpoint factor plays in the sequences matching process. Specifically, our approach consists of two components. The first one attempts to complement the original pose-incomplete information carried by the sequences with synthetic GAN-generated images, and fuse their feature vectors into a more discriminative viewpoint-insensitive embedding, namely Weighted Fusion (WF). Another one performs an explicit pose-based alignment of sequence pairs to promote coherent feature matching, namely Weighted-Pose Regulation (WPR). Extensive experiments on two large video-based benchmark datasets show that our approach outperforms considerably existing methods.
Tasks	Person Re-Identification, Video-Based Person Re-Identification
Published	2019-03-27
URL	http://arxiv.org/abs/1903.11552v1
PDF	http://arxiv.org/pdf/1903.11552v1.pdf
PWC	https://paperswithcode.com/paper/gan-based-pose-aware-regulation-for-video
Repo
Framework

On the generalization of GAN image forensics


Title	On the generalization of GAN image forensics
Authors	Xinsheng Xuan, Bo Peng, Wei Wang, Jing Dong
Abstract	Recently the GAN generated face images are more and more realistic with high-quality, even hard for human eyes to detect. On the other hand, the forensics community keeps on developing methods to detect these generated fake images and try to guarantee the credibility of visual contents. Although researchers have developed some methods to detect generated images, few of them explore the important problem of generalization ability of forensics model. As new types of GANs are emerging fast, the generalization ability of forensics models to detect new types of GAN images is absolutely an essential research topic. In this paper, we explore this problem and propose to use preprocessed images to train a forensic CNN model. By applying similar image level preprocessing to both real and fake training images, the forensics model is forced to learn more intrinsic features to classify the generated and real face images. Our experimental results also prove the effectiveness of the proposed method.
Tasks	GAN image forensics
Published	2019-02-27
URL	https://arxiv.org/abs/1902.11153v2
PDF	https://arxiv.org/pdf/1902.11153v2.pdf
PWC	https://paperswithcode.com/paper/on-the-generalization-of-gan-image-forensics
Repo
Framework

Estimating uncertainty of earthquake rupture using Bayesian neural network


Title	Estimating uncertainty of earthquake rupture using Bayesian neural network
Authors	Sabber Ahamed
Abstract	Bayesian neural networks (BNN) are the probabilistic model that combines the strengths of both neural network (NN) and stochastic processes. As a result, BNN can combat overfitting and perform well in applications where data is limited. Earthquake rupture study is such a problem where data is insufficient, and scientists have to rely on many trial and error numerical or physical models. Lack of resources and computational expenses, often, it becomes hard to determine the reasons behind the earthquake rupture. In this work, a BNN has been used (1) to combat the small data problem and (2) to find out the parameter combinations responsible for earthquake rupture and (3) to estimate the uncertainty associated with earthquake rupture. Two thousand rupture simulations are used to train and test the model. A simple 2D rupture geometry is considered where the fault has a Gaussian geometric heterogeneity at the center, and eight parameters vary in each simulation. The test F1-score of BNN (0.8334), which is 2.34% higher than plain NN score. Results show that the parameters of rupture propagation have higher uncertainty than the rupture arrest. Normal stresses play a vital role in determining rupture propagation and are also the highest source of uncertainty, followed by the dynamic friction coefficient. Shear stress has a moderate role, whereas the geometric features such as the width and height of the fault are least significant and uncertain.
Tasks
Published	2019-11-21
URL	https://arxiv.org/abs/1911.09660v1
PDF	https://arxiv.org/pdf/1911.09660v1.pdf
PWC	https://paperswithcode.com/paper/estimating-uncertainty-of-earthquake-rupture
Repo
Framework

Three algorithms for solving high-dimensional fully-coupled FBSDEs through deep learning


Title	Three algorithms for solving high-dimensional fully-coupled FBSDEs through deep learning
Authors	Shaolin Ji, Shige Peng, Ying Peng, Xichuan Zhang
Abstract	Recently, the deep learning method has been used for solving forward-backward stochastic differential equations (FBSDEs) and parabolic partial differential equations (PDEs). It has good accuracy and performance for high-dimensional problems. In this paper, we mainly solve fully coupled FBSDEs through deep learning and provide three algorithms. Several numerical results show remarkable performance especially for high-dimensional cases.
Tasks
Published	2019-07-11
URL	https://arxiv.org/abs/1907.05327v4
PDF	https://arxiv.org/pdf/1907.05327v4.pdf
PWC	https://paperswithcode.com/paper/three-algorithms-for-solving-high-dimensional
Repo
Framework


Title	Accelerating the Computation of UCB and Related Indices for Reinforcement Learning
Authors	Wesley Cowan, Michael N. Katehakis, Daniel Pirutinsky
Abstract	In this paper we derive an efficient method for computing the indices associated with an asymptotically optimal upper confidence bound algorithm (MDP-UCB) of Burnetas and Katehakis (1997) that only requires solving a system of two non-linear equations with two unknowns, irrespective of the cardinality of the state space of the Markovian decision process (MDP). In addition, we develop a similar acceleration for computing the indices for the MDP-Deterministic Minimum Empirical Divergence (MDP-DMED) algorithm developed in Cowan et al. (2019), based on ideas from Honda and Takemura (2011), that involves solving a single equation of one variable. We provide experimental results demonstrating the computational time savings and regret performance of these algorithms. In these comparison we also consider the Optimistic Linear Programming (OLP) algorithm (Tewari and Bartlett, 2008) and a method based on Posterior sampling (MDP-PS).
Tasks
Published	2019-09-28
URL	https://arxiv.org/abs/1909.13158v1
PDF	https://arxiv.org/pdf/1909.13158v1.pdf
PWC	https://paperswithcode.com/paper/accelerating-the-computation-of-ucb-and
Repo
Framework

BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions


Title	BoolQ: Exploring the Surprising Difficulty of Natural Yes/No Questions
Authors	Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, Kristina Toutanova
Abstract	In this paper we study yes/no questions that are naturally occurring — meaning that they are generated in unprompted and unconstrained settings. We build a reading comprehension dataset, BoolQ, of such questions, and show that they are unexpectedly challenging. They often query for complex, non-factoid information, and require difficult entailment-like inference to solve. We also explore the effectiveness of a range of transfer learning baselines. We find that transferring from entailment data is more effective than transferring from paraphrase or extractive QA data, and that it, surprisingly, continues to be very beneficial even when starting from massive pre-trained language models such as BERT. Our best method trains BERT on MultiNLI and then re-trains it on our train set. It achieves 80.4% accuracy compared to 90% accuracy of human annotators (and 62% majority-baseline), leaving a significant gap for future work.
Tasks	Reading Comprehension, Transfer Learning
Published	2019-05-24
URL	https://arxiv.org/abs/1905.10044v1
PDF	https://arxiv.org/pdf/1905.10044v1.pdf
PWC	https://paperswithcode.com/paper/boolq-exploring-the-surprising-difficulty-of
Repo
Framework

Nowcasting Recessions using the SVM Machine Learning Algorithm


Title	Nowcasting Recessions using the SVM Machine Learning Algorithm
Authors	Alexander James, Yaser S. Abu-Mostafa, Xiao Qiao
Abstract	We introduce a novel application of Support Vector Machines (SVM), an important Machine Learning algorithm, to determine the beginning and end of recessions in real time. Nowcasting, “forecasting” a condition about the present time because the full information about it is not available until later, is key for recessions, which are only determined months after the fact. We show that SVM has excellent predictive performance for this task, and we provide implementation details to facilitate its use in similar problems in economics and finance.
Tasks
Published	2019-02-17
URL	https://arxiv.org/abs/1903.03202v2
PDF	https://arxiv.org/pdf/1903.03202v2.pdf
PWC	https://paperswithcode.com/paper/nowcasting-recessions-using-the-svm-machine
Repo
Framework

A Generalization of Principal Component Analysis


Title	A Generalization of Principal Component Analysis
Authors	Samuele Battaglino, Erdem Koyuncu
Abstract	Conventional principal component analysis (PCA) finds a principal vector that maximizes the sum of second powers of principal components. We consider a generalized PCA that aims at maximizing the sum of an arbitrary convex function of principal components. We present a gradient ascent algorithm to solve the problem. For the kernel version of generalized PCA, we show that the solutions can be obtained as fixed points of a simple single-layer recurrent neural network. We also evaluate our algorithms on different datasets.
Tasks
Published	2019-10-29
URL	https://arxiv.org/abs/1910.13511v2
PDF	https://arxiv.org/pdf/1910.13511v2.pdf
PWC	https://paperswithcode.com/paper/a-generalization-of-principal-component
Repo
Framework

Heuristics in Multi-Winner Approval Voting


Title	Heuristics in Multi-Winner Approval Voting
Authors	Jaelle Scheuerman, Jason L. Harman, Nicholas Mattei, K. Brent Venable
Abstract	In many real world situations, collective decisions are made using voting. Moreover, scenarios such as committee or board elections require voting rules that return multiple winners. In multi-winner approval voting (AV), an agent may vote for as many candidates as they wish. Winners are chosen by tallying up the votes and choosing the top-$k$ candidates receiving the most votes. An agent may manipulate the vote to achieve a better outcome by voting in a way that does not reflect their true preferences. In complex and uncertain situations, agents may use heuristics to strategize, instead of incurring the additional effort required to compute the manipulation which most favors them. In this paper, we examine voting behavior in multi-winner approval voting scenarios with complete information. We show that people generally manipulate their vote to obtain a better outcome, but often do not identify the optimal manipulation. Instead, voters tend to prioritize the candidates with the highest utilities. Using simulations, we demonstrate the effectiveness of these heuristics in situations where agents only have access to partial information.
Tasks
Published	2019-05-28
URL	https://arxiv.org/abs/1905.12104v2
PDF	https://arxiv.org/pdf/1905.12104v2.pdf
PWC	https://paperswithcode.com/paper/heuristics-in-multi-winner-approval-voting
Repo
Framework

Variance Reduced Stochastic Proximal Algorithm for AUC Maximization


Title	Variance Reduced Stochastic Proximal Algorithm for AUC Maximization
Authors	Soham Dan, Dushyant Sahoo
Abstract	Stochastic Gradient Descent has been widely studied with classification accuracy as a performance measure. However, these stochastic algorithms cannot be directly used when non-decomposable pairwise performance measures are used such as Area under the ROC curve (AUC) which is a common performance metric when the classes are imbalanced. There have been several algorithms proposed for optimizing AUC as a performance metric, and one of the recent being a stochastic proximal gradient algorithm (SPAM). But the downside of the stochastic methods is that they suffer from high variance leading to slower convergence. To combat this issue, several variance reduced methods have been proposed with faster convergence guarantees than vanilla stochastic gradient descent. Again, these variance reduced methods are not directly applicable when non-decomposable performance measures are used. In this paper, we develop a Variance Reduced Stochastic Proximal algorithm for AUC Maximization (\textsc{VRSPAM}) and perform a theoretical analysis as well as empirical analysis to show that our algorithm converges faster than SPAM which is the previous state-of-the-art for the AUC maximization problem.
Tasks
Published	2019-11-08
URL	https://arxiv.org/abs/1911.03548v1
PDF	https://arxiv.org/pdf/1911.03548v1.pdf
PWC	https://paperswithcode.com/paper/variance-reduced-stochastic-proximal
Repo
Framework