October 16, 2019

2908 words 14 mins read

Paper Group ANR 1125

Paper Group ANR 1125

Person Re-Identification by Semantic Region Representation and Topology Constraint. Rigid Point Registration with Expectation Conditional Maximization. Transfer Learning for Improving Speech Emotion Classification Accuracy. Characterizing Diseases and disorders in Gay Users’ tweets. A General Framework for Counterfactual Learning-to-Rank. Enhancing …

Person Re-Identification by Semantic Region Representation and Topology Constraint

Title Person Re-Identification by Semantic Region Representation and Topology Constraint
Authors Jianjun Lei, Lijie Niu, Huazhu Fu, Bo Peng, Qingming Huang, Chunping Hou
Abstract Person re-identification is a popular research topic which aims at matching the specific person in a multi-camera network automatically. Feature representation and metric learning are two important issues for person re-identification. In this paper, we propose a novel person re-identification method, which consists of a reliable representation called Semantic Region Representation (SRR), and an effective metric learning with Mapping Space Topology Constraint (MSTC). The SRR integrates semantic representations to achieve effective similarity comparison between the corresponding regions via parsing the body into multiple parts, which focuses on the foreground context against the background interference. To learn a discriminant metric, the MSTC is proposed to take into account the topological relationship among all samples in the feature space. It considers two-fold constraints: the distribution of positive pairs should be more compact than the average distribution of negative pairs with regard to the same probe, while the average distance between different classes should be larger than that between same classes. These two aspects cooperate to maintain the compactness of the intra-class as well as the sparsity of the inter-class. Extensive experiments conducted on five challenging person re-identification datasets, VIPeR, SYSU-sReID, QUML GRID, CUHK03, and Market-1501, show that the proposed method achieves competitive performance with the state-of-the-art approaches.
Tasks Metric Learning, Person Re-Identification
Published 2018-08-20
URL http://arxiv.org/abs/1808.06280v1
PDF http://arxiv.org/pdf/1808.06280v1.pdf
PWC https://paperswithcode.com/paper/person-re-identification-by-semantic-region
Repo
Framework

Rigid Point Registration with Expectation Conditional Maximization

Title Rigid Point Registration with Expectation Conditional Maximization
Authors Jing Wu
Abstract This paper addresses the issue of matching rigid 3D object points with 2D image points through point registration based on maximum likelihood principle in computer simulated images. Perspective projection is necessary when transforming 3D coordinate into 2D. The problem then recasts into a missing data framework where unknown correspondences are handled via mixture models. Adopting the Expectation Conditional Maximization for Point Registration (ECMPR), two different rotation and translation optimization algorithms are compared in this paper. We analyze in detail the associated consequences in terms of estimation of the registration parameters theoretically and experimentally.
Tasks
Published 2018-03-07
URL http://arxiv.org/abs/1803.02518v1
PDF http://arxiv.org/pdf/1803.02518v1.pdf
PWC https://paperswithcode.com/paper/rigid-point-registration-with-expectation
Repo
Framework

Transfer Learning for Improving Speech Emotion Classification Accuracy

Title Transfer Learning for Improving Speech Emotion Classification Accuracy
Authors Siddique Latif, Rajib Rana, Shahzad Younis, Junaid Qadir, Julien Epps
Abstract The majority of existing speech emotion recognition research focuses on automatic emotion detection using training and testing data from same corpus collected under the same conditions. The performance of such systems has been shown to drop significantly in cross-corpus and cross-language scenarios. To address the problem, this paper exploits a transfer learning technique to improve the performance of speech emotion recognition systems that is novel in cross-language and cross-corpus scenarios. Evaluations on five different corpora in three different languages show that Deep Belief Networks (DBNs) offer better accuracy than previous approaches on cross-corpus emotion recognition, relative to a Sparse Autoencoder and SVM baseline system. Results also suggest that using a large number of languages for training and using a small fraction of the target data in training can significantly boost accuracy compared with baseline also for the corpus with limited training examples.
Tasks Emotion Classification, Emotion Recognition, Speech Emotion Recognition, Transfer Learning
Published 2018-01-19
URL http://arxiv.org/abs/1801.06353v3
PDF http://arxiv.org/pdf/1801.06353v3.pdf
PWC https://paperswithcode.com/paper/transfer-learning-for-improving-speech
Repo
Framework

Characterizing Diseases and disorders in Gay Users’ tweets

Title Characterizing Diseases and disorders in Gay Users’ tweets
Authors Frank Webb, Amir Karami, Vanessa Kitzie
Abstract A lack of information exists about the health issues of lesbian, gay, bisexual, transgender, and queer (LGBTQ) people who are often excluded from national demographic assessments, health studies, and clinical trials. As a result, medical experts and researchers lack a holistic understanding of the health disparities facing these populations. Fortunately, publicly available social media data such as Twitter data can be utilized to support the decisions of public health policy makers and managers with respect to LGBTQ people. This research employs a computational approach to collect tweets from gay users on health-related topics and model these topics. To determine the nature of health-related information shared by men who have sex with men on Twitter, we collected thousands of tweets from 177 active users. We sampled these tweets using a framework that can be applied to other LGBTQ sub-populations in future research. We found 11 diseases in 7 categories based on ICD 10 that are in line with the published studies and official reports.
Tasks
Published 2018-03-24
URL http://arxiv.org/abs/1803.09134v1
PDF http://arxiv.org/pdf/1803.09134v1.pdf
PWC https://paperswithcode.com/paper/characterizing-diseases-and-disorders-in-gay
Repo
Framework

A General Framework for Counterfactual Learning-to-Rank

Title A General Framework for Counterfactual Learning-to-Rank
Authors Aman Agarwal, Kenta Takatsu, Ivan Zaitsev, Thorsten Joachims
Abstract Implicit feedback (e.g., click, dwell time) is an attractive source of training data for Learning-to-Rank, but its naive use leads to learning results that are distorted by presentation bias. For the special case of optimizing average rank for linear ranking functions, however, the recently developed SVM-PropRank method has shown that counterfactual inference techniques can be used to provably overcome the distorting effect of presentation bias. Going beyond this special case, this paper provides a general and theoretically rigorous framework for counterfactual learning-to-rank that enables unbiased training for a broad class of additive ranking metrics (e.g., Discounted Cumulative Gain (DCG)) as well as a broad class of models (e.g., deep networks). Specifically, we derive a relaxation for propensity-weighted rank-based metrics which is subdifferentiable and thus suitable for gradient-based optimization. We demonstrate the effectiveness of this general approach by instantiating two new learning methods. One is a new type of unbiased SVM that optimizes DCG – called SVM PropDCG –, and we show how the resulting optimization problem can be solved via the Convex Concave Procedure (CCP). The other is Deep PropDCG, where the ranking function can be an arbitrary deep network. In addition to the theoretical support, we empirically find that SVM PropDCG significantly outperforms existing linear rankers in terms of DCG. Moreover, the ability to train non-linear ranking functions via Deep PropDCG further improves performance.
Tasks Counterfactual Inference, Learning-To-Rank
Published 2018-04-30
URL https://arxiv.org/abs/1805.00065v3
PDF https://arxiv.org/pdf/1805.00065v3.pdf
PWC https://paperswithcode.com/paper/counterfactual-learning-to-rank-for-additive
Repo
Framework

Enhancing the efficiency of quantum annealing via reinforcement: A path-integral Monte Carlo simulation of the quantum reinforcement algorithm

Title Enhancing the efficiency of quantum annealing via reinforcement: A path-integral Monte Carlo simulation of the quantum reinforcement algorithm
Authors A. Ramezanpour
Abstract The standard quantum annealing algorithm tries to approach the ground state of a classical system by slowly decreasing the hopping rates of a quantum random walk in the configuration space of the problem, where the on-site energies are provided by the classical energy function. In a quantum reinforcement algorithm, the annealing works instead by increasing gradually the strength of the on-site energies according to the probability of finding the walker on each site of the configuration space. Here, by using the path-integral Monte Carlo simulations of the quantum algorithms, we show that annealing via reinforcement can significantly enhance the success probability of the quantum walker. More precisely, we implement a local version of the quantum reinforcement algorithm, where the system wave function is replaced by an approximate wave function using the local expectation values of the system. We use this algorithm to find solutions to a prototypical constraint satisfaction problem (XORSAT) close to the satisfiability to unsatisfiability phase transition. The study is limited to small problem sizes (a few hundreds of variables), nevertheless, the numerical results suggest that quantum reinforcement may provide a useful strategy to deal with other computationally hard problems and larger problem sizes even as a classical optimization algorithm.
Tasks
Published 2018-12-06
URL http://arxiv.org/abs/1812.02569v1
PDF http://arxiv.org/pdf/1812.02569v1.pdf
PWC https://paperswithcode.com/paper/enhancing-the-efficiency-of-quantum-annealing
Repo
Framework

Modeling Stated Preference for Mobility-on-Demand Transit: A Comparison of Machine Learning and Logit Models

Title Modeling Stated Preference for Mobility-on-Demand Transit: A Comparison of Machine Learning and Logit Models
Authors Xilei Zhao, Xiang Yan, Alan Yu, Pascal Van Hentenryck
Abstract Logit models are usually applied when studying individual travel behavior, i.e., to predict travel mode choice and to gain behavioral insights on traveler preferences. Recently, some studies have applied machine learning to model travel mode choice and reported higher out-of-sample predictive accuracy than traditional logit models (e.g., multinomial logit). However, little research focuses on comparing the interpretability of machine learning with logit models. In other words, how to draw behavioral insights from the high-performance “black-box” machine-learning models remains largely unsolved in the field of travel behavior modeling. This paper aims at providing a comprehensive comparison between the two approaches by examining the key similarities and differences in model development, evaluation, and behavioral interpretation between logit and machine-learning models for travel mode choice modeling. To complement the theoretical discussions, the paper also empirically evaluates the two approaches on the stated-preference survey data for a new type of transit system integrating high-frequency fixed-route services and ridesourcing. The results show that machine learning can produce significantly higher predictive accuracy than logit models. Moreover, machine learning and logit models largely agree on many aspects of behavioral interpretations. In addition, machine learning can automatically capture the nonlinear relationship between the input features and choice outcomes. The paper concludes that there is great potential in merging ideas from machine learning and conventional statistical methods to develop refined models for travel behavior research and suggests some new research directions.
Tasks
Published 2018-11-04
URL http://arxiv.org/abs/1811.01315v2
PDF http://arxiv.org/pdf/1811.01315v2.pdf
PWC https://paperswithcode.com/paper/modeling-stated-preference-for-mobility-on
Repo
Framework

Deep Image Compression via End-to-End Learning

Title Deep Image Compression via End-to-End Learning
Authors Haojie Liu, Tong Chen, Qiu Shen, Tao Yue, Zhan Ma
Abstract We present a lossy image compression method based on deep convolutional neural networks (CNNs), which outperforms the existing BPG, WebP, JPEG2000 and JPEG as measured via multi-scale structural similarity (MS-SSIM), at the same bit rate. Currently, most of the CNNs based approaches train the network using a L2 loss between the reconstructions and the ground-truths in the pixel domain, which leads to over-smoothing results and visual quality degradation especially at a very low bit rate. Therefore, we improve the subjective quality with the combination of a perception loss and an adversarial loss additionally. To achieve better rate-distortion optimization (RDO), we also introduce an easy-to-hard transfer learning when adding quantization error and rate constraint. Finally, we evaluate our method on public Kodak and the Test Dataset P/M released by the Computer Vision Lab of ETH Zurich, resulting in averaged 7.81% and 19.1% BD-rate reduction over BPG, respectively.
Tasks Image Compression, Quantization, Transfer Learning
Published 2018-06-05
URL http://arxiv.org/abs/1806.01496v1
PDF http://arxiv.org/pdf/1806.01496v1.pdf
PWC https://paperswithcode.com/paper/deep-image-compression-via-end-to-end
Repo
Framework

Faster Neural Network Training with Approximate Tensor Operations

Title Faster Neural Network Training with Approximate Tensor Operations
Authors Menachem Adelman, Mark Silberstein
Abstract We propose a novel technique for faster Neural Network (NN) training by systematically approximating all the constituent matrix multiplications and convolutions. This approach is complementary to other approximation techniques, requires no changes to the dimensions of the network layers, hence compatible with existing training frameworks. We first analyze the applicability of the existing methods for approximating matrix multiplication to NN training, and extend the most suitable column-row sampling algorithm to approximating multi-channel convolutions. We apply approximate tensor operations to training MLP, CNN and LSTM network architectures on MNIST, CIFAR-100 and Penn Tree Bank datasets and demonstrate 30%-80% reduction in the amount of computations while maintaining little or no impact on the test accuracy. Our promising results encourage further study of general methods for approximating tensor operations and their application to NN training.
Tasks
Published 2018-05-21
URL http://arxiv.org/abs/1805.08079v1
PDF http://arxiv.org/pdf/1805.08079v1.pdf
PWC https://paperswithcode.com/paper/faster-neural-network-training-with
Repo
Framework

Algorithms for solving optimization problems arising from deep neural net models: nonsmooth problems

Title Algorithms for solving optimization problems arising from deep neural net models: nonsmooth problems
Authors Vyacheslav Kungurtsev, Tomas Pevny
Abstract Machine Learning models incorporating multiple layered learning networks have been seen to provide effective models for various classification problems. The resulting optimization problem to solve for the optimal vector minimizing the empirical risk is, however, highly nonconvex. This alone presents a challenge to application and development of appropriate optimization algorithms for solving the problem. However, in addition, there are a number of interesting problems for which the objective function is non- smooth and nonseparable. In this paper, we summarize the primary challenges involved, the state of the art, and present some numerical results on an interesting and representative class of problems.
Tasks
Published 2018-06-30
URL http://arxiv.org/abs/1807.00173v1
PDF http://arxiv.org/pdf/1807.00173v1.pdf
PWC https://paperswithcode.com/paper/algorithms-for-solving-optimization-problems
Repo
Framework

Satellite Imagery Multiscale Rapid Detection with Windowed Networks

Title Satellite Imagery Multiscale Rapid Detection with Windowed Networks
Authors Adam Van Etten
Abstract Detecting small objects over large areas remains a significant challenge in satellite imagery analytics. Among the challenges is the sheer number of pixels and geographical extent per image: a single DigitalGlobe satellite image encompasses over 64 km2 and over 250 million pixels. Another challenge is that objects of interest are often minuscule (~pixels in extent even for the highest resolution imagery), which complicates traditional computer vision techniques. To address these issues, we propose a pipeline (SIMRDWN) that evaluates satellite images of arbitrarily large size at native resolution at a rate of > 0.2 km2/s. Building upon the tensorflow object detection API paper, this pipeline offers a unified approach to multiple object detection frameworks that can run inference on images of arbitrary size. The SIMRDWN pipeline includes a modified version of YOLO (known as YOLT), along with the models of the tensorflow object detection API: SSD, Faster R-CNN, and R-FCN. The proposed approach allows comparison of the performance of these four frameworks, and can rapidly detect objects of vastly different scales with relatively little training data over multiple sensors. For objects of very different scales (e.g. airplanes versus airports) we find that using two different detectors at different scales is very effective with negligible runtime cost.We evaluate large test images at native resolution and find mAP scores of 0.2 to 0.8 for vehicle localization, with the YOLT architecture achieving both the highest mAP and fastest inference speed.
Tasks Object Detection
Published 2018-09-25
URL http://arxiv.org/abs/1809.09978v1
PDF http://arxiv.org/pdf/1809.09978v1.pdf
PWC https://paperswithcode.com/paper/satellite-imagery-multiscale-rapid-detection
Repo
Framework

Latent heterogeneous multilayer community detection

Title Latent heterogeneous multilayer community detection
Authors Hafiz Tiomoko Ali, Sijia Liu, Yasin Yilmaz, Romain Couillet, Indika Rajapakse, Alfred Hero
Abstract We propose a method for simultaneously detecting shared and unshared communities in heterogeneous multilayer weighted and undirected networks. The multilayer network is assumed to follow a generative probabilistic model that takes into account the similarities and dissimilarities between the communities. We make use of a variational Bayes approach for jointly inferring the shared and unshared hidden communities from multilayer network observations. We show that our approach outperforms state-of-the-art algorithms in detecting disparate (shared and private) communities on synthetic data as well as on real genome-wide fibroblast proliferation dataset.
Tasks Community Detection
Published 2018-06-16
URL https://arxiv.org/abs/1806.07963v2
PDF https://arxiv.org/pdf/1806.07963v2.pdf
PWC https://paperswithcode.com/paper/latent-heterogeneous-multilayer-community
Repo
Framework

KI, Philosophie, Logik

Title KI, Philosophie, Logik
Authors Karl Schlechta
Abstract This is a short (and personal) introduction in German to the connections between artificial intelligence, philosophy, and logic, and to the author’s work. Dies ist eine kurze (und persoenliche) Einfuehrung in die Zusammenhaenge zwischen Kuenstlicher Intelligenz, Philosophie, und Logik, und in die Arbeiten des Autors.
Tasks
Published 2018-12-27
URL http://arxiv.org/abs/1901.00365v1
PDF http://arxiv.org/pdf/1901.00365v1.pdf
PWC https://paperswithcode.com/paper/ki-philosophie-logik
Repo
Framework

Iteratively Training Look-Up Tables for Network Quantization

Title Iteratively Training Look-Up Tables for Network Quantization
Authors Fabien Cardinaux, Stefan Uhlich, Kazuki Yoshiyama, Javier Alonso García, Stephen Tiedemann, Thomas Kemp, Akira Nakamura
Abstract Operating deep neural networks on devices with limited resources requires the reduction of their memory footprints and computational requirements. In this paper we introduce a training method, called look-up table quantization, LUT-Q, which learns a dictionary and assigns each weight to one of the dictionary’s values. We show that this method is very flexible and that many other techniques can be seen as special cases of LUT-Q. For example, we can constrain the dictionary trained with LUT-Q to generate networks with pruned weight matrices or restrict the dictionary to powers-of-two to avoid the need for multiplications. In order to obtain fully multiplier-less networks, we also introduce a multiplier-less version of batch normalization. Extensive experiments on image recognition and object detection tasks show that LUT-Q consistently achieves better performance than other methods with the same quantization bitwidth.
Tasks Object Detection, Quantization
Published 2018-11-13
URL http://arxiv.org/abs/1811.05355v1
PDF http://arxiv.org/pdf/1811.05355v1.pdf
PWC https://paperswithcode.com/paper/iteratively-training-look-up-tables-for
Repo
Framework

Early Stopping for Nonparametric Testing

Title Early Stopping for Nonparametric Testing
Authors Meimei Liu, Guang Cheng
Abstract Early stopping of iterative algorithms is an algorithmic regularization method to avoid over-fitting in estimation and classification. In this paper, we show that early stopping can also be applied to obtain the minimax optimal testing in a general non-parametric setup. Specifically, a Wald-type test statistic is obtained based on an iterated estimate produced by functional gradient descent algorithms in a reproducing kernel Hilbert space. A notable contribution is to establish a “sharp” stopping rule: when the number of iterations achieves an optimal order, testing optimality is achievable; otherwise, testing optimality becomes impossible. As a by-product, a similar sharpness result is also derived for minimax optimal estimation under early stopping studied in [11] and [19]. All obtained results hold for various kernel classes, including Sobolev smoothness classes and Gaussian kernel classes.
Tasks
Published 2018-05-25
URL http://arxiv.org/abs/1805.09950v3
PDF http://arxiv.org/pdf/1805.09950v3.pdf
PWC https://paperswithcode.com/paper/early-stopping-for-nonparametric-testing
Repo
Framework
comments powered by Disqus