April 2, 2020

Paper Group ANR 257

Statistically Guided Divide-and-Conquer for Sparse Factorization of Large Matrix. Multi-Stream Networks and Ground-Truth Generation for Crowd Counting. “Why is ‘Chicago’ deceptive?” Towards Building Model-Driven Tutorials for Humans. Trees, forests, and impurity-based variable importance. Explaining the Explainer: A First Theoretical Analysis of LI …

Statistically Guided Divide-and-Conquer for Sparse Factorization of Large Matrix

Title Statistically Guided Divide-and-Conquer for Sparse Factorization of Large Matrix
Authors Kun Chen, Ruipeng Dong, Wanwan Xu, Zemin Zheng
Abstract The sparse factorization of a large matrix is fundamental in modern statistical learning. In particular, the sparse singular value decomposition and its variants have been utilized in multivariate regression, factor analysis, biclustering, vector time series modeling, among others. The appeal of this factorization is owing to its power in discovering a highly-interpretable latent association network, either between samples and variables or between responses and predictors. However, many existing methods are either ad hoc without a general performance guarantee, or are computationally intensive, rendering them unsuitable for large-scale studies. We formulate the statistical problem as a sparse factor regression and tackle it with a divide-and-conquer approach. In the first stage of division, we consider both sequential and parallel approaches for simplifying the task into a set of co-sparse unit-rank estimation (CURE) problems, and establish the statistical underpinnings of these commonly-adopted and yet poorly understood deflation methods. In the second stage of division, we innovate a contended stagewise learning technique, consisting of a sequence of simple incremental updates, to efficiently trace out the whole solution paths of CURE. Our algorithm has a much lower computational complexity than alternating convex search, and the choice of the step size enables a flexible and principled tradeoff between statistical accuracy and computational efficiency. Our work is among the first to enable stagewise learning for non-convex problems, and the idea can be applicable in many multi-convex problems. Extensive simulation studies and an application in genetics demonstrate the effectiveness and scalability of our approach.
Published 2020-03-17
URL https://arxiv.org/abs/2003.07898v1
PDF https://arxiv.org/pdf/2003.07898v1.pdf
PWC https://paperswithcode.com/paper/statistically-guided-divide-and-conquer-for
Repo
Framework

Multi-Stream Networks and Ground-Truth Generation for Crowd Counting

Title Multi-Stream Networks and Ground-Truth Generation for Crowd Counting
Authors Rodolfo Quispe, Darwin Ttito, Adín Ramírez Rivera, Helio Pedrini
Abstract Crowd scene analysis has received a lot of attention recently due to the wide variety of applications, for instance, forensic science, urban planning, surveillance and security. In this context, a challenging task is known as crowd counting, whose main purpose is to estimate the number of people present in a single image. A Multi-Stream Convolutional Neural Network is developed and evaluated in this work, which receives an image as input and produces a density map that represents the spatial distribution of people in an end-to-end fashion. In order to address complex crowd counting issues, such as extremely unconstrained scale and perspective changes, the network architecture utilizes receptive fields with different size filters for each stream. In addition, we investigate the influence of the two most common fashions on the generation of ground truths and propose a hybrid method based on tiny face detection and scale interpolation. Experiments conducted on two challenging datasets, UCF-CC-50 and ShanghaiTech, demonstrate that using our ground truth generation methods achieves superior results.
Published 2020-02-23
URL https://arxiv.org/abs/2002.09951v3
PDF https://arxiv.org/pdf/2002.09951v3.pdf
PWC https://paperswithcode.com/paper/multi-stream-networks-and-ground-truth
Repo
Framework

“Why is ‘Chicago’ deceptive?” Towards Building Model-Driven Tutorials for Humans

Title “Why is ‘Chicago’ deceptive?” Towards Building Model-Driven Tutorials for Humans
Authors Vivian Lai, Han Liu, Chenhao Tan
Abstract To support human decision making with machine learning models, we often need to elucidate patterns embedded in the models that are unsalient, unknown, or counterintuitive to humans. While existing approaches focus on explaining machine predictions with real-time assistance, we explore model-driven tutorials to help humans understand these patterns in a training phase. We consider both tutorials with guidelines from scientific papers, analogous to current practices of science communication, and automatically selected examples from training data with explanations. We use deceptive review detection as a testbed and conduct large-scale, randomized human-subject experiments to examine the effectiveness of such tutorials. We find that tutorials indeed improve human performance, with and without real-time assistance. In particular, although deep learning provides superior predictive performance than simple models, tutorials and explanations from simple models are more useful to humans. Our work suggests future directions for human-centered tutorials and explanations towards a synergy between humans and AI.
Published 2020-01-14
URL https://arxiv.org/abs/2001.05871v1
PDF https://arxiv.org/pdf/2001.05871v1.pdf
PWC https://paperswithcode.com/paper/why-is-chicago-deceptive-towards-building
Repo
Framework

Trees, forests, and impurity-based variable importance

Title Trees, forests, and impurity-based variable importance
Authors Erwan Scornet
Abstract Tree ensemble methods such as random forests [Breiman, 2001] are very popular to handle high-dimensional tabular data sets, notably because of their good predictive accuracy. However, when machine learning is used for decision-making problems, settling for the best predictive procedures may not be reasonable since enlightened decisions require an in-depth comprehension of the algorithm prediction process. Unfortunately, random forests are not intrinsically interpretable since their prediction results from averaging several hundreds of decision trees. A classic approach to gain knowledge on this so-called black-box algorithm is to compute variable importances, that are employed to assess the predictive impact of each input variable. Variable importances are then used to rank or select variables and thus play a great role in data analysis. Nevertheless, there is no justification to use random forest variable importances in such way: we do not even know what these quantities estimate. In this paper, we analyze one of the two well-known random forest variable importances, the Mean Decrease Impurity (MDI). We prove that if input variables are independent and in absence of interactions, MDI provides a variance decomposition of the output, where the contribution of each variable is clearly identified. We also study models exhibiting dependence between input variables or interaction, for which the variable importance is intrinsically ill-defined. Our analysis shows that there may exist some benefits to use a forest compared to a single tree.
Published 2020-01-13
URL https://arxiv.org/abs/2001.04295v1
PDF https://arxiv.org/pdf/2001.04295v1.pdf
PWC https://paperswithcode.com/paper/trees-forests-and-impurity-based-variable
Repo
Framework

Explaining the Explainer: A First Theoretical Analysis of LIME

Title Explaining the Explainer: A First Theoretical Analysis of LIME
Authors Damien Garreau, Ulrike von Luxburg
Abstract Machine learning is used more and more often for sensitive applications, sometimes replacing humans in critical decision-making processes. As such, interpretability of these algorithms is a pressing need. One popular algorithm to provide interpretability is LIME (Local Interpretable Model-Agnostic Explanation). In this paper, we provide the first theoretical analysis of LIME. We derive closed-form expressions for the coefficients of the interpretable model when the function to explain is linear. The good news is that these coefficients are proportional to the gradient of the function to explain: LIME indeed discovers meaningful features. However, our analysis also reveals that poor choices of parameters can lead LIME to miss important features.
Published 2020-01-10
URL https://arxiv.org/abs/2001.03447v2
PDF https://arxiv.org/pdf/2001.03447v2.pdf
PWC https://paperswithcode.com/paper/explaining-the-explainer-a-first-theoretical
Repo
Framework

Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width

Title Taylorized Training: Towards Better Approximation of Neural Network Training at Finite Width
Authors Yu Bai, Ben Krause, Huan Wang, Caiming Xiong, Richard Socher
Abstract We propose \emph{Taylorized training} as an initiative towards better understanding neural network training at finite width. Taylorized training involves training the $k$-th order Taylor expansion of the neural network at initialization, and is a principled extension of linearized training—a recently proposed theory for understanding the success of deep learning. We experiment with Taylorized training on modern neural network architectures, and show that Taylorized training (1) agrees with full neural network training increasingly better as we increase $k$, and (2) can significantly close the performance gap between linearized and full training. Compared with linearized training, higher-order training works in more realistic settings such as standard parameterization and large (initial) learning rate. We complement our experiments with theoretical results showing that the approximation error of $k$-th order Taylorized models decay exponentially over $k$ in wide neural networks.
Published 2020-02-10
URL https://arxiv.org/abs/2002.04010v2
PDF https://arxiv.org/pdf/2002.04010v2.pdf
PWC https://paperswithcode.com/paper/taylorized-training-towards-better
Repo
Framework

Hybrid Graph Neural Networks for Crowd Counting

Title Hybrid Graph Neural Networks for Crowd Counting
Authors Ao Luo, Fan Yang, Xin Li, Dong Nie, Zhicheng Jiao, Shangchen Zhou, Hong Cheng
Abstract Crowd counting is an important yet challenging task due to the large scale and density variation. Recent investigations have shown that distilling rich relations among multi-scale features and exploiting useful information from the auxiliary task, i.e., localization, are vital for this task. Nevertheless, how to comprehensively leverage these relations within a unified network architecture is still a challenging problem. In this paper, we present a novel network structure called Hybrid Graph Neural Network (HyGnn) which targets to relieve the problem by interweaving the multi-scale features for crowd density as well as its auxiliary task (localization) together and performing joint reasoning over a graph. Specifically, HyGnn integrates a hybrid graph to jointly represent the task-specific feature maps of different scales as nodes, and two types of relations as edges:(i) multi-scale relations for capturing the feature dependencies across scales and (ii) mutual beneficial relations building bridges for the cooperation between counting and localization. Thus, through message passing, HyGnn can distill rich relations between the nodes to obtain more powerful representations, leading to robust and accurate results. Our HyGnn performs significantly well on four challenging datasets: ShanghaiTech Part A, ShanghaiTech Part B, UCF_CC_50 and UCF_QNRF, outperforming the state-of-the-art approaches by a large margin.
Published 2020-01-31
URL https://arxiv.org/abs/2002.00092v1
PDF https://arxiv.org/pdf/2002.00092v1.pdf
PWC https://paperswithcode.com/paper/hybrid-graph-neural-networks-for-crowd
Repo
Framework

iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention

Title iqiyi Submission to ActivityNet Challenge 2019 Kinetics-700 challenge: Hierarchical Group-wise Attention
Authors Qian Liu, Dongyang Cai, Jie Liu, Nan Ding, Tao Wang
Abstract In this report, the method for the iqiyi submission to the task of ActivityNet 2019 Kinetics-700 challenge is described. Three models are involved in the model ensemble stage: TSN, HG-NL and StNet. We propose the hierarchical group-wise non-local (HG-NL) module for frame-level features aggregation for video classification. The standard non-local (NL) module is effective in aggregating frame-level features on the task of video classification but presents low parameters efficiency and high computational cost. The HG-NL method involves a hierarchical group-wise structure and generates multiple attention maps to enhance performance. Basing on this hierarchical group-wise structure, the proposed method has competitive accuracy, fewer parameters and smaller computational cost than the standard NL. For the task of ActivityNet 2019 Kinetics-700 challenge, after model ensemble, we finally obtain an averaged top-1 and top-5 error percentage 28.444% on the test set.
Published 2020-02-07
URL https://arxiv.org/abs/2002.02918v1
PDF https://arxiv.org/pdf/2002.02918v1.pdf
PWC https://paperswithcode.com/paper/iqiyi-submission-to-activitynet-challenge
Repo
Framework

Commentaries on “Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception” [Science Robotics Vol. 4 Issue 30 (2019) 1-10

Title Commentaries on “Learning Sensorimotor Control with Neuromorphic Sensors: Toward Hyperdimensional Active Perception” [Science Robotics Vol. 4 Issue 30 (2019) 1-10
Authors Denis Kleyko, Ross W. Gayler, Evgeny Osipov
Abstract This correspondence comments on the findings reported in a recent Science Robotics article by Mitrokhin et al. [1]. The main goal of this commentary is to expand on some of the issues touched on in that article. Our experience is that hyperdimensional computing is very different from other approaches to computation and that it can take considerable exposure to its concepts before attaining practically useful understanding. Therefore, in order to provide an overview of the area to the first time reader of [1], the commentary includes a brief historic overview as well as connects the findings of the article to a larger body of literature existing in the area.
Published 2020-03-25
URL https://arxiv.org/abs/2003.11458v1
PDF https://arxiv.org/pdf/2003.11458v1.pdf
PWC https://paperswithcode.com/paper/commentaries-on-learning-sensorimotor-control
Repo
Framework

Self-Supervised Poisson-Gaussian Denoising

Title Self-Supervised Poisson-Gaussian Denoising
Authors Wesley Khademi, Sonia Rao, Clare Minnerath, Guy Hagen, Jonathan Ventura
Abstract We extend the blindspot model for self-supervised denoising to handle Poisson-Gaussian noise and introduce an improved training scheme that avoids hyperparameters and adapts the denoiser to the test data. Self-supervised models for denoising learn to denoise from only noisy data and do not require corresponding clean images, which are difficult or impossible to acquire in some application areas of interest such as low-light microscopy. We introduce a new training strategy to handle Poisson-Gaussian noise which is the standard noise model for microscope images. Our new strategy eliminates hyperparameters from the loss function, which is important in a self-supervised regime where no ground truth data is available to guide hyperparameter tuning. We show how our denoiser can be adapted to the test data to improve performance. Our evaluation on a microscope image denoising benchmark validates our approach.
Published 2020-02-21
URL https://arxiv.org/abs/2002.09558v1
PDF https://arxiv.org/pdf/2002.09558v1.pdf
PWC https://paperswithcode.com/paper/self-supervised-poisson-gaussian-denoising
Repo
Framework

NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis

Title NoiseBreaker: Gradual Image Denoising Guided by Noise Analysis
Authors Florian Lemarchand, Erwan Nogues, Maxime Pelcat
Abstract Fully supervised deep-learning based denoisers are currently the most performing image denoising solutions. However, they require clean reference images. When the target noise is complex, e.g. composed of an unknown mixture of primary noises with unknown intensity, fully supervised solutions are limited by the difficulty to build a suited training set for the problem. This paper proposes a gradual denoising strategy that iteratively detects the dominating noise in an image, and removes it using a tailored denoiser. The method is shown to keep up with state of the art blind denoisers on mixture noises. Moreover, noise analysis is demonstrated to guide denoisers efficiently not only on noise type, but also on noise intensity. The method provides an insight on the nature of the encountered noise, and it makes it possible to extend an existing denoiser with new noise nature. This feature makes the method adaptive to varied denoising cases.
Published 2020-02-18
URL https://arxiv.org/abs/2002.07487v1
PDF https://arxiv.org/pdf/2002.07487v1.pdf
Repo
Framework

Noise2Inverse: Self-supervised deep convolutional denoising for linear inverse problems in imaging

Title Noise2Inverse: Self-supervised deep convolutional denoising for linear inverse problems in imaging
Authors Allard A. Hendriksen, Daniel M. Pelt, K. Joost Batenburg
Abstract Recovering a high-quality image from noisy indirect measurement is an important problem with many applications. For such inverse problems, supervised deep convolutional neural network (CNN)-based denoising methods have shown strong results, but their success critically depends on the availability of a high-quality training dataset of similar measurements. For image denoising, methods are available that enable training without a separate training dataset by assuming that the noise in two different pixels is uncorrelated. However, this assumption does not hold for inverse problems, resulting in artifacts in the output of existing methods. Here, we propose Noise2Inverse, a deep CNN-based denoising method for linear inverse problems in imaging that does not require any additional clean or noisy data. Training a CNN-based denoiser is enabled by exploiting the noise model to compute multiple statistically independent reconstructions. We develop a theoretical framework which shows that such training indeed obtains a denoising CNN, assuming the measured noise is element-wise independent and zero-mean. On simulated CT datasets, Noise2Inverse demonstrates a substantial improvement in peak signal-to-noise ratio (> 2dB) and structural similarity index (> 30%) compared to image denoising methods and conventional reconstruction methods, such as Total-Variation Minimization. We also demonstrate that the method is able to significantly reduce noise in challenging real-world experimental datasets.
Published 2020-01-31
URL https://arxiv.org/abs/2001.11801v1
PDF https://arxiv.org/pdf/2001.11801v1.pdf
PWC https://paperswithcode.com/paper/noise2inverse-self-supervised-deep
Repo
Framework

Stochastic tree ensembles for regularized nonlinear regression

Title Stochastic tree ensembles for regularized nonlinear regression
Authors Jingyu He, P. Richard Hahn
Abstract This paper develops a novel stochastic tree ensemble method for nonlinear regression, which we refer to as XBART, short for Accelerated Bayesian Additive Regression Trees. By combining regularization and stochastic search strategies from Bayesian modeling with computationally efficient techniques from recursive partitioning approaches, the new method attains state-of-the-art performance: in many settings it is both faster and more accurate than the widely-used XGBoost algorithm. Via careful simulation studies, we demonstrate that our new approach provides accurate point-wise estimates of the mean function and does so faster than popular alternatives, such as BART, XGBoost and neural networks (using Keras). We also prove a number of basic theoretical results about the new algorithm, including consistency of the single tree version of the model and stationarity of the Markov chain produced by the ensemble version. Furthermore, we demonstrate that initializing standard Bayesian additive regression trees Markov chain Monte Carlo (MCMC) at XBART-fitted trees considerably improves credible interval coverage and reduces total run-time.
Published 2020-02-09
URL https://arxiv.org/abs/2002.03375v1
PDF https://arxiv.org/pdf/2002.03375v1.pdf
PWC https://paperswithcode.com/paper/stochastic-tree-ensembles-for-regularized
Repo
Framework

Deriving Emotions and Sentiments from Visual Content: A Disaster Analysis Use Case

Title Deriving Emotions and Sentiments from Visual Content: A Disaster Analysis Use Case
Authors Kashif Ahmad, Syed Zohaib, Nicola Conci, Ala Al-Fuqaha
Abstract Sentiment analysis aims to extract and express a person’s perception, opinions and emotions towards an entity, object, product and a service, enabling businesses to obtain feedback from the consumers. The increasing popularity of the social networks and users’ tendency towards sharing their feelings, expressions and opinions in text, visual and audio content has opened new opportunities and challenges in sentiment analysis. While sentiment analysis of text streams has been widely explored in the literature, sentiment analysis of images and videos is relatively new. This article introduces visual sentiment analysis and contrasts it with textual sentiment analysis with emphasis on the opportunities and challenges in this nascent research area. We also propose a deep visual sentiment analyzer for disaster-related images as a use-case, covering different aspects of visual sentiment analysis starting from data collection, annotation, model selection, implementation and evaluations. We believe such rigorous analysis will provide a baseline for future research in the domain.
Published 2020-02-03
URL https://arxiv.org/abs/2002.03773v1
PDF https://arxiv.org/pdf/2002.03773v1.pdf
PWC https://paperswithcode.com/paper/deriving-emotions-and-sentiments-from-visual
Repo
Framework

Emotion and Sentiment Lexicon Impact on Sentiment Analysis Applied to Book Reviews

Title Emotion and Sentiment Lexicon Impact on Sentiment Analysis Applied to Book Reviews
Authors Patrice Bellot, Lerch Soëlie, Bruno Emmanuel, Murisasco Elisabeth
Abstract Consumers are used to consulting posted reviews on the Internet before buying a product. But it’s difficult to know the global opinion considering the important number of those reviews. Sentiment analysis afford detecting polarity (positive, negative, neutral) in a expressed opinion and therefore classifying those reviews. Our purpose is to determine the influence of emotions on the polarity of books reviews. We define “bag-of-words” representation models of reviews which use a lexicon containing emotional (anticipation, sadness, fear, anger, joy, surprise, trust, disgust) and sentimental (positive, negative) words. This lexicon afford measuring felt emotions types by readers. The implemented supervised learning used is a Random Forest type. The application concerns Amazon platform’s reviews. Mots-cl{'e}s : Analyse de sentiments, Analyse d’{'e}motions (texte), Classification de polarit{'e} de sentiments