Paper Group ANR 421
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks. Fast Black-box Variational Inference through Stochastic Trust-Region Optimization. Quantized Minimum Error Entropy Criterion. e-Counterfeit: a mobile-server platform for document counterfeit detection. Learning Deep Energy Models: Contrastive Diver …
Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks
| Title | Visual Explanation by Interpretation: Improving Visual Feedback Capabilities of Deep Neural Networks |
| Authors | Jose Oramas, Kaili Wang, Tinne Tuytelaars |
| Abstract | Interpretation and explanation of deep models is critical towards wide adoption of systems that rely on them. In this paper, we propose a novel scheme for both interpretation as well as explanation in which, given a pretrained model, we automatically identify internal features relevant for the set of classes considered by the model, without relying on additional annotations. We interpret the model through average visualizations of this reduced set of features. Then, at test time, we explain the network prediction by accompanying the predicted class label with supporting visualizations derived from the identified features. In addition, we propose a method to address the artifacts introduced by stridded operations in deconvNet-based visualizations. Moreover, we introduce an8Flower, a dataset specifically designed for objective quantitative evaluation of methods for visual explanation.Experiments on the MNIST,ILSVRC12,Fashion144k and an8Flower datasets show that our method produces detailed explanations with good coverage of relevant features of the classes of interest |
| Tasks | |
| Published | 2017-12-18 |
| URL | http://arxiv.org/abs/1712.06302v3 |
| http://arxiv.org/pdf/1712.06302v3.pdf | |
| PWC | https://paperswithcode.com/paper/visual-explanation-by-interpretation |
| Repo | |
| Framework | |
Fast Black-box Variational Inference through Stochastic Trust-Region Optimization
| Title | Fast Black-box Variational Inference through Stochastic Trust-Region Optimization |
| Authors | Jeffrey Regier, Michael I. Jordan, Jon McAuliffe |
| Abstract | We introduce TrustVI, a fast second-order algorithm for black-box variational inference based on trust-region optimization and the reparameterization trick. At each iteration, TrustVI proposes and assesses a step based on minibatches of draws from the variational distribution. The algorithm provably converges to a stationary point. We implemented TrustVI in the Stan framework and compared it to two alternatives: Automatic Differentiation Variational Inference (ADVI) and Hessian-free Stochastic Gradient Variational Inference (HFSGVI). The former is based on stochastic first-order optimization. The latter uses second-order information, but lacks convergence guarantees. TrustVI typically converged at least one order of magnitude faster than ADVI, demonstrating the value of stochastic second-order information. TrustVI often found substantially better variational distributions than HFSGVI, demonstrating that our convergence theory can matter in practice. |
| Tasks | |
| Published | 2017-06-07 |
| URL | http://arxiv.org/abs/1706.02375v2 |
| http://arxiv.org/pdf/1706.02375v2.pdf | |
| PWC | https://paperswithcode.com/paper/fast-black-box-variational-inference-through |
| Repo | |
| Framework | |
Quantized Minimum Error Entropy Criterion
| Title | Quantized Minimum Error Entropy Criterion |
| Authors | Badong Chen, Lei Xing, Nanning Zheng, Jose C. Príncipe |
| Abstract | Comparing with traditional learning criteria, such as mean square error (MSE), the minimum error entropy (MEE) criterion is superior in nonlinear and non-Gaussian signal processing and machine learning. The argument of the logarithm in Renyis entropy estimator, called information potential (IP), is a popular MEE cost in information theoretic learning (ITL). The computational complexity of IP is however quadratic in terms of sample number due to double summation. This creates computational bottlenecks especially for large-scale datasets. To address this problem, in this work we propose an efficient quantization approach to reduce the computational burden of IP, which decreases the complexity from O(N*N) to O (MN) with M « N. The new learning criterion is called the quantized MEE (QMEE). Some basic properties of QMEE are presented. Illustrative examples are provided to verify the excellent performance of QMEE. |
| Tasks | Quantization |
| Published | 2017-10-11 |
| URL | http://arxiv.org/abs/1710.04089v2 |
| http://arxiv.org/pdf/1710.04089v2.pdf | |
| PWC | https://paperswithcode.com/paper/quantized-minimum-error-entropy-criterion |
| Repo | |
| Framework | |
e-Counterfeit: a mobile-server platform for document counterfeit detection
| Title | e-Counterfeit: a mobile-server platform for document counterfeit detection |
| Authors | Albert Berenguel, Oriol Ramos Terrades, Josep Lladós, Cristina Cañero |
| Abstract | This paper presents a novel application to detect counterfeit identity documents forged by a scan-printing operation. Texture analysis approaches are proposed to extract validation features from security background that is usually printed in documents as IDs or banknotes. The main contribution of this work is the end-to-end mobile-server architecture, which provides a service for non-expert users and therefore can be used in several scenarios. The system also provides a crowdsourcing mode so labeled images can be gathered, generating databases for incremental training of the algorithms. |
| Tasks | Texture Classification |
| Published | 2017-08-21 |
| URL | http://arxiv.org/abs/1708.06126v1 |
| http://arxiv.org/pdf/1708.06126v1.pdf | |
| PWC | https://paperswithcode.com/paper/e-counterfeit-a-mobile-server-platform-for |
| Repo | |
| Framework | |
Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE
| Title | Learning Deep Energy Models: Contrastive Divergence vs. Amortized MLE |
| Authors | Qiang Liu, Dilin Wang |
| Abstract | We propose a number of new algorithms for learning deep energy models and demonstrate their properties. We show that our SteinCD performs well in term of test likelihood, while SteinGAN performs well in terms of generating realistic looking images. Our results suggest promising directions for learning better models by combining GAN-style methods with traditional energy-based learning. |
| Tasks | |
| Published | 2017-07-04 |
| URL | http://arxiv.org/abs/1707.00797v1 |
| http://arxiv.org/pdf/1707.00797v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-deep-energy-models-contrastive |
| Repo | |
| Framework | |
A History of Metaheuristics
| Title | A History of Metaheuristics |
| Authors | Kenneth Sorensen, Marc Sevaux, Fred Glover |
| Abstract | This chapter describes the history of metaheuristics in five distinct periods, starting long before the first use of the term and ending a long time in the future. |
| Tasks | |
| Published | 2017-04-04 |
| URL | http://arxiv.org/abs/1704.00853v1 |
| http://arxiv.org/pdf/1704.00853v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-history-of-metaheuristics |
| Repo | |
| Framework | |
Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion
| Title | Simultaneous Facial Landmark Detection, Pose and Deformation Estimation under Facial Occlusion |
| Authors | Yue Wu, Chao Gou, Qiang Ji |
| Abstract | Facial landmark detection, head pose estimation, and facial deformation analysis are typical facial behavior analysis tasks in computer vision. The existing methods usually perform each task independently and sequentially, ignoring their interactions. To tackle this problem, we propose a unified framework for simultaneous facial landmark detection, head pose estimation, and facial deformation analysis, and the proposed model is robust to facial occlusion. Following a cascade procedure augmented with model-based head pose estimation, we iteratively update the facial landmark locations, facial occlusion, head pose and facial de- formation until convergence. The experimental results on benchmark databases demonstrate the effectiveness of the proposed method for simultaneous facial landmark detection, head pose and facial deformation estimation, even if the images are under facial occlusion. |
| Tasks | Facial Landmark Detection, Head Pose Estimation, Pose Estimation |
| Published | 2017-09-23 |
| URL | http://arxiv.org/abs/1709.08130v1 |
| http://arxiv.org/pdf/1709.08130v1.pdf | |
| PWC | https://paperswithcode.com/paper/simultaneous-facial-landmark-detection-pose |
| Repo | |
| Framework | |
Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior
| Title | Rethinking generalization requires revisiting old ideas: statistical mechanics approaches and complex learning behavior |
| Authors | Charles H. Martin, Michael W. Mahoney |
| Abstract | We describe an approach to understand the peculiar and counterintuitive generalization properties of deep neural networks. The approach involves going beyond worst-case theoretical capacity control frameworks that have been popular in machine learning in recent years to revisit old ideas in the statistical mechanics of neural networks. Within this approach, we present a prototypical Very Simple Deep Learning (VSDL) model, whose behavior is controlled by two control parameters, one describing an effective amount of data, or load, on the network (that decreases when noise is added to the input), and one with an effective temperature interpretation (that increases when algorithms are early stopped). Using this model, we describe how a very simple application of ideas from the statistical mechanics theory of generalization provides a strong qualitative description of recently-observed empirical results regarding the inability of deep neural networks not to overfit training data, discontinuous learning and sharp transitions in the generalization properties of learning algorithms, etc. |
| Tasks | |
| Published | 2017-10-26 |
| URL | http://arxiv.org/abs/1710.09553v2 |
| http://arxiv.org/pdf/1710.09553v2.pdf | |
| PWC | https://paperswithcode.com/paper/rethinking-generalization-requires-revisiting |
| Repo | |
| Framework | |
Active Collaborative Ensemble Tracking
| Title | Active Collaborative Ensemble Tracking |
| Authors | Kourosh Meshgi, Maryam Sadat Mirzaei, Shigeyuki Oba, Shin Ishii |
| Abstract | A discriminative ensemble tracker employs multiple classifiers, each of which casts a vote on all of the obtained samples. The votes are then aggregated in an attempt to localize the target object. Such method relies on collective competence and the diversity of the ensemble to approach the target/non-target classification task from different views. However, by updating all of the ensemble using a shared set of samples and their final labels, such diversity is lost or reduced to the diversity provided by the underlying features or internal classifiers’ dynamics. Additionally, the classifiers do not exchange information with each other while striving to serve the collective goal, i.e., better classification. In this study, we propose an active collaborative information exchange scheme for ensemble tracking. This, not only orchestrates different classifier towards a common goal but also provides an intelligent update mechanism to keep the diversity of classifiers and to mitigate the shortcomings of one with the others. The data exchange is optimized with regard to an ensemble uncertainty utility function, and the ensemble is updated via co-training. The evaluations demonstrate promising results realized by the proposed algorithm for the real-world online tracking. |
| Tasks | |
| Published | 2017-04-28 |
| URL | http://arxiv.org/abs/1704.08821v1 |
| http://arxiv.org/pdf/1704.08821v1.pdf | |
| PWC | https://paperswithcode.com/paper/active-collaborative-ensemble-tracking |
| Repo | |
| Framework | |
Smartphone Based Colorimetric Detection via Machine Learning
| Title | Smartphone Based Colorimetric Detection via Machine Learning |
| Authors | Ali Y. Mutlu, Volkan Kılıç, Gizem K. Özdemir, Abdullah Bayram, Nesrin Horzum, Mehmet E. Solmaz |
| Abstract | We report the application of machine learning to smartphone based colorimetric detection of pH values. The strip images were used as the training set for Least Squares-Support Vector Machine (LS-SVM) classifier algorithms that were able to successfully classify the distinct pH values. The difference in the obtained image formats was found not to significantly affect the performance of the proposed machine learning approach. Moreover, the influence of the illumination conditions on the perceived color of pH strips was investigated and further experiments were carried out to study effect of color change on the learning model. Test results on JPEG, RAW and RAW-corrected image formats captured in different lighting conditions lead to perfect classification accuracy, sensitivity and specificity, which proves that the colorimetric detection using machine learning based systems is able to adapt to various experimental conditions and is a great candidate for smartphone based sensing in paper-based colorimetric assays. |
| Tasks | |
| Published | 2017-03-17 |
| URL | http://arxiv.org/abs/1703.10217v1 |
| http://arxiv.org/pdf/1703.10217v1.pdf | |
| PWC | https://paperswithcode.com/paper/smartphone-based-colorimetric-detection-via |
| Repo | |
| Framework | |
Gini-regularized Optimal Transport with an Application to Spatio-Temporal Forecasting
| Title | Gini-regularized Optimal Transport with an Application to Spatio-Temporal Forecasting |
| Authors | Lucas Roberts, Leo Razoumov, Lin Su, Yuyang Wang |
| Abstract | Rapidly growing product lines and services require a finer-granularity forecast that considers geographic locales. However the open question remains, how to assess the quality of a spatio-temporal forecast? In this manuscript we introduce a metric to evaluate spatio-temporal forecasts. This metric is based on an Opti- mal Transport (OT) problem. The metric we propose is a constrained OT objec- tive function using the Gini impurity function as a regularizer. We demonstrate through computer experiments both the qualitative and the quantitative charac- teristics of the Gini regularized OT problem. Moreover, we show that the Gini regularized OT problem converges to the classical OT problem, when the Gini regularized problem is considered as a function of {\lambda}, the regularization parame-ter. The convergence to the classical OT solution is faster than the state-of-the-art Entropic-regularized OT[Cuturi, 2013] and results in a numerically more stable algorithm. |
| Tasks | Spatio-Temporal Forecasting |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02512v1 |
| http://arxiv.org/pdf/1712.02512v1.pdf | |
| PWC | https://paperswithcode.com/paper/gini-regularized-optimal-transport-with-an |
| Repo | |
| Framework | |
Ratio Utility and Cost Analysis for Privacy Preserving Subspace Projection
| Title | Ratio Utility and Cost Analysis for Privacy Preserving Subspace Projection |
| Authors | Mert Al, Shibiao Wan, Sun-Yuan Kung |
| Abstract | With a rapidly increasing number of devices connected to the internet, big data has been applied to various domains of human life. Nevertheless, it has also opened new venues for breaching users’ privacy. Hence it is highly required to develop techniques that enable data owners to privatize their data while keeping it useful for intended applications. Existing methods, however, do not offer enough flexibility for controlling the utility-privacy trade-off and may incur unfavorable results when privacy requirements are high. To tackle these drawbacks, we propose a compressive-privacy based method, namely RUCA (Ratio Utility and Cost Analysis), which can not only maximize performance for a privacy-insensitive classification task but also minimize the ability of any classifier to infer private information from the data. Experimental results on Census and Human Activity Recognition data sets demonstrate that RUCA significantly outperforms existing privacy preserving data projection techniques for a wide range of privacy pricings. |
| Tasks | Activity Recognition, Human Activity Recognition |
| Published | 2017-02-26 |
| URL | http://arxiv.org/abs/1702.07976v1 |
| http://arxiv.org/pdf/1702.07976v1.pdf | |
| PWC | https://paperswithcode.com/paper/ratio-utility-and-cost-analysis-for-privacy |
| Repo | |
| Framework | |
Summarizing Dialogic Arguments from Social Media
| Title | Summarizing Dialogic Arguments from Social Media |
| Authors | Amita Misra, Shereen Oraby, Shubhangi Tandon, Sharath TS, Pranav Anand, Marilyn Walker |
| Abstract | Online argumentative dialog is a rich source of information on popular beliefs and opinions that could be useful to companies as well as governmental or public policy agencies. Compact, easy to read, summaries of these dialogues would thus be highly valuable. A priori, it is not even clear what form such a summary should take. Previous work on summarization has primarily focused on summarizing written texts, where the notion of an abstract of the text is well defined. We collect gold standard training data consisting of five human summaries for each of 161 dialogues on the topics of Gay Marriage, Gun Control and Abortion. We present several different computational models aimed at identifying segments of the dialogues whose content should be used for the summary, using linguistic features and Word2vec features with both SVMs and Bidirectional LSTMs. We show that we can identify the most important arguments by using the dialog context with a best F-measure of 0.74 for gun control, 0.71 for gay marriage, and 0.67 for abortion. |
| Tasks | |
| Published | 2017-10-31 |
| URL | http://arxiv.org/abs/1711.00092v1 |
| http://arxiv.org/pdf/1711.00092v1.pdf | |
| PWC | https://paperswithcode.com/paper/summarizing-dialogic-arguments-from-social |
| Repo | |
| Framework | |
Learning to Learn: Meta-Critic Networks for Sample Efficient Learning
| Title | Learning to Learn: Meta-Critic Networks for Sample Efficient Learning |
| Authors | Flood Sung, Li Zhang, Tao Xiang, Timothy Hospedales, Yongxin Yang |
| Abstract | We propose a novel and flexible approach to meta-learning for learning-to-learn from only a few examples. Our framework is motivated by actor-critic reinforcement learning, but can be applied to both reinforcement and supervised learning. The key idea is to learn a meta-critic: an action-value function neural network that learns to criticise any actor trying to solve any specified task. For supervised learning, this corresponds to the novel idea of a trainable task-parametrised loss generator. This meta-critic approach provides a route to knowledge transfer that can flexibly deal with few-shot and semi-supervised conditions for both reinforcement and supervised learning. Promising results are shown on both reinforcement and supervised learning problems. |
| Tasks | Meta-Learning, Transfer Learning |
| Published | 2017-06-29 |
| URL | http://arxiv.org/abs/1706.09529v1 |
| http://arxiv.org/pdf/1706.09529v1.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-learn-meta-critic-networks-for |
| Repo | |
| Framework | |
Using SVDD in SimpleMKL for 3D-Shapes Filtering
| Title | Using SVDD in SimpleMKL for 3D-Shapes Filtering |
| Authors | Gaëlle Loosli, Hattoibe Aboubacar |
| Abstract | This paper proposes the adaptation of Support Vector Data Description (SVDD) to the multiple kernel case (MK-SVDD), based on SimpleMKL. It also introduces a variant called Slim-MK-SVDD that is able to produce a tighter frontier around the data. For the sake of comparison, the equivalent methods are also developed for One-Class SVM, known to be very similar to SVDD for certain shapes of kernels. Those algorithms are illustrated in the context of 3D-shapes filtering and outliers detection. For the 3D-shapes problem, the objective is to be able to select a sub-category of 3D-shapes, each sub-category being learned with our algorithm in order to create a filter. For outliers detection, we apply the proposed algorithms for unsupervised outliers detection as well as for the supervised case. |
| Tasks | |
| Published | 2017-12-07 |
| URL | http://arxiv.org/abs/1712.02658v1 |
| http://arxiv.org/pdf/1712.02658v1.pdf | |
| PWC | https://paperswithcode.com/paper/using-svdd-in-simplemkl-for-3d-shapes |
| Repo | |
| Framework | |
