Paper Group ANR 206
Relevance Subject Machine: A Novel Person Re-identification Framework. Robust Maximum Likelihood Estimation of Sparse Vector Error Correction Model. Efficient mixture model for clustering of sparse high dimensional binary data. Robust Guided Image Filtering. Active Image-based Modeling with a Toy Drone. Nesterov’s Acceleration For Approximate Newto …
Relevance Subject Machine: A Novel Person Re-identification Framework
| Title | Relevance Subject Machine: A Novel Person Re-identification Framework |
| Authors | Igor Fedorov, Ritwik Giri, Bhaskar D. Rao, Truong Q. Nguyen |
| Abstract | We propose a novel method called the Relevance Subject Machine (RSM) to solve the person re-identification (re-id) problem. RSM falls under the category of Bayesian sparse recovery algorithms and uses the sparse representation of the input video under a pre-defined dictionary to identify the subject in the video. Our approach focuses on the multi-shot re-id problem, which is the prevalent problem in many video analytics applications. RSM captures the essence of the multi-shot re-id problem by constraining the support of the sparse codes for each input video frame to be the same. Our proposed approach is also robust enough to deal with time varying outliers and occlusions by introducing a sparse, non-stationary noise term in the model error. We provide a novel Variational Bayesian based inference procedure along with an intuitive interpretation of the proposed update rules. We evaluate our approach over several commonly used re-id datasets and show superior performance over current state-of-the-art algorithms. Specifically, for ILIDS-VID, a recent large scale re-id dataset, RSM shows significant improvement over all published approaches, achieving an 11.5% (absolute) improvement in rank 1 accuracy over the closest competing algorithm considered. |
| Tasks | Person Re-Identification |
| Published | 2017-03-30 |
| URL | http://arxiv.org/abs/1703.10645v1 |
| http://arxiv.org/pdf/1703.10645v1.pdf | |
| PWC | https://paperswithcode.com/paper/relevance-subject-machine-a-novel-person-re |
| Repo | |
| Framework | |
Robust Maximum Likelihood Estimation of Sparse Vector Error Correction Model
| Title | Robust Maximum Likelihood Estimation of Sparse Vector Error Correction Model |
| Authors | Ziping Zhao, Daniel P. Palomar |
| Abstract | In econometrics and finance, the vector error correction model (VECM) is an important time series model for cointegration analysis, which is used to estimate the long-run equilibrium variable relationships. The traditional analysis and estimation methodologies assume the underlying Gaussian distribution but, in practice, heavy-tailed data and outliers can lead to the inapplicability of these methods. In this paper, we propose a robust model estimation method based on the Cauchy distribution to tackle this issue. In addition, sparse cointegration relations are considered to realize feature selection and dimension reduction. An efficient algorithm based on the majorization-minimization (MM) method is applied to solve the proposed nonconvex problem. The performance of this algorithm is shown through numerical simulations. |
| Tasks | Dimensionality Reduction, Feature Selection, Time Series |
| Published | 2017-10-16 |
| URL | http://arxiv.org/abs/1710.05513v1 |
| http://arxiv.org/pdf/1710.05513v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-maximum-likelihood-estimation-of |
| Repo | |
| Framework | |
Efficient mixture model for clustering of sparse high dimensional binary data
| Title | Efficient mixture model for clustering of sparse high dimensional binary data |
| Authors | Marek Śmieja, Krzysztof Hajto, Jacek Tabor |
| Abstract | In this paper we propose a mixture model, SparseMix, for clustering of sparse high dimensional binary data, which connects model-based with centroid-based clustering. Every group is described by a representative and a probability distribution modeling dispersion from this representative. In contrast to classical mixture models based on EM algorithm, SparseMix: -is especially designed for the processing of sparse data, -can be efficiently realized by an on-line Hartigan optimization algorithm, -is able to automatically reduce unnecessary clusters. We perform extensive experimental studies on various types of data, which confirm that SparseMix builds partitions with higher compatibility with reference grouping than related methods. Moreover, constructed representatives often better reveal the internal structure of data. |
| Tasks | |
| Published | 2017-07-11 |
| URL | http://arxiv.org/abs/1707.03157v1 |
| http://arxiv.org/pdf/1707.03157v1.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-mixture-model-for-clustering-of |
| Repo | |
| Framework | |
Robust Guided Image Filtering
| Title | Robust Guided Image Filtering |
| Authors | Wei Liu, Xiaogang Chen, Chunhua Shen, Jingyi Yu, Qiang Wu, Jie Yang |
| Abstract | The process of using one image to guide the filtering process of another one is called Guided Image Filtering (GIF). The main challenge of GIF is the structure inconsistency between the guidance image and the target image. Besides, noise in the target image is also a challenging issue especially when it is heavy. In this paper, we propose a general framework for Robust Guided Image Filtering (RGIF), which contains a data term and a smoothness term, to solve the two issues mentioned above. The data term makes our model simultaneously denoise the target image and perform GIF which is robust against the heavy noise. The smoothness term is able to make use of the property of both the guidance image and the target image which is robust against the structure inconsistency. While the resulting model is highly non-convex, it can be solved through the proposed Iteratively Re-weighted Least Squares (IRLS) in an efficient manner. For challenging applications such as guided depth map upsampling, we further develop a data-driven parameter optimization scheme to properly determine the parameter in our model. This optimization scheme can help to preserve small structures and sharp depth edges even for a large upsampling factor (8x for example). Moreover, the specially designed structure of the data term and the smoothness term makes our model perform well in edge-preserving smoothing for single-image tasks (i.e., the guidance image is the target image itself). This paper is an extension of our previous work [1], [2]. |
| Tasks | |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09379v1 |
| http://arxiv.org/pdf/1703.09379v1.pdf | |
| PWC | https://paperswithcode.com/paper/robust-guided-image-filtering |
| Repo | |
| Framework | |
Active Image-based Modeling with a Toy Drone
| Title | Active Image-based Modeling with a Toy Drone |
| Authors | Rui Huang, Danping Zou, Richard Vaughan, Ping Tan |
| Abstract | Image-based modeling techniques can now generate photo-realistic 3D models from images. But it is up to users to provide high quality images with good coverage and view overlap, which makes the data capturing process tedious and time consuming. We seek to automate data capturing for image-based modeling. The core of our system is an iterative linear method to solve the multi-view stereo (MVS) problem quickly and plan the Next-Best-View (NBV) effectively. Our fast MVS algorithm enables online model reconstruction and quality assessment to determine the NBVs on the fly. We test our system with a toy unmanned aerial vehicle (UAV) in simulated, indoor and outdoor experiments. Results show that our system improves the efficiency of data acquisition and ensures the completeness of the final model. |
| Tasks | |
| Published | 2017-05-02 |
| URL | http://arxiv.org/abs/1705.01010v3 |
| http://arxiv.org/pdf/1705.01010v3.pdf | |
| PWC | https://paperswithcode.com/paper/active-image-based-modeling-with-a-toy-drone |
| Repo | |
| Framework | |
Nesterov’s Acceleration For Approximate Newton
| Title | Nesterov’s Acceleration For Approximate Newton |
| Authors | Haishan Ye, Zhihua Zhang |
| Abstract | Optimization plays a key role in machine learning. Recently, stochastic second-order methods have attracted much attention due to their low computational cost in each iteration. However, these algorithms might perform poorly especially if it is hard to approximate the Hessian well and efficiently. As far as we know, there is no effective way to handle this problem. In this paper, we resort to Nesterov’s acceleration technique to improve the convergence performance of a class of second-order methods called approximate Newton. We give a theoretical analysis that Nesterov’s acceleration technique can improve the convergence performance for approximate Newton just like for first-order methods. We accordingly propose an accelerated regularized sub-sampled Newton. Our accelerated algorithm performs much better than the original regularized sub-sampled Newton in experiments, which validates our theory empirically. Besides, the accelerated regularized sub-sampled Newton has good performance comparable to or even better than classical algorithms. |
| Tasks | |
| Published | 2017-10-17 |
| URL | http://arxiv.org/abs/1710.08496v1 |
| http://arxiv.org/pdf/1710.08496v1.pdf | |
| PWC | https://paperswithcode.com/paper/nesterovs-acceleration-for-approximate-newton |
| Repo | |
| Framework | |
Towards Interpretable R-CNN by Unfolding Latent Structures
| Title | Towards Interpretable R-CNN by Unfolding Latent Structures |
| Authors | Tianfu Wu, Wei Sun, Xilai Li, Xi Song, Bo Li |
| Abstract | This paper first proposes a method of formulating model interpretability in visual understanding tasks based on the idea of unfolding latent structures. It then presents a case study in object detection using popular two-stage region-based convolutional network (i.e., R-CNN) detection systems. We focus on weakly-supervised extractive rationale generation, that is learning to unfold latent discriminative part configurations of object instances automatically and simultaneously in detection without using any supervision for part configurations. We utilize a top-down hierarchical and compositional grammar model embedded in a directed acyclic AND-OR Graph (AOG) to explore and unfold the space of latent part configurations of regions of interest (RoIs). We propose an AOGParsing operator to substitute the RoIPooling operator widely used in R-CNN. In detection, a bounding box is interpreted by the best parse tree derived from the AOG on-the-fly, which is treated as the qualitatively extractive rationale generated for interpreting detection. We propose a folding-unfolding method to train the AOG and convolutional networks end-to-end. In experiments, we build on R-FCN and test our method on the PASCAL VOC 2007 and 2012 datasets. We show that the method can unfold promising latent structures without hurting the performance. |
| Tasks | Object Detection |
| Published | 2017-11-14 |
| URL | http://arxiv.org/abs/1711.05226v2 |
| http://arxiv.org/pdf/1711.05226v2.pdf | |
| PWC | https://paperswithcode.com/paper/towards-interpretable-r-cnn-by-unfolding |
| Repo | |
| Framework | |
Unifying the Stochastic Spectral Descent for Restricted Boltzmann Machines with Bernoulli or Gaussian Inputs
| Title | Unifying the Stochastic Spectral Descent for Restricted Boltzmann Machines with Bernoulli or Gaussian Inputs |
| Authors | Kai Fan |
| Abstract | Stochastic gradient descent based algorithms are typically used as the general optimization tools for most deep learning models. A Restricted Boltzmann Machine (RBM) is a probabilistic generative model that can be stacked to construct deep architectures. For RBM with Bernoulli inputs, non-Euclidean algorithm such as stochastic spectral descent (SSD) has been specifically designed to speed up the convergence with improved use of the gradient estimation by sampling methods. However, the existing algorithm and corresponding theoretical justification depend on the assumption that the possible configurations of inputs are finite, like binary variables. The purpose of this paper is to generalize SSD for Gaussian RBM being capable of mod- eling continuous data, regardless of the previous assumption. We propose the gradient descent methods in non-Euclidean space of parameters, via de- riving the upper bounds of logarithmic partition function for RBMs based on Schatten-infinity norm. We empirically show that the advantage and improvement of SSD over stochastic gradient descent (SGD). |
| Tasks | |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09766v1 |
| http://arxiv.org/pdf/1703.09766v1.pdf | |
| PWC | https://paperswithcode.com/paper/unifying-the-stochastic-spectral-descent-for |
| Repo | |
| Framework | |
Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning
| Title | Weakly-supervised Relation Extraction by Pattern-enhanced Embedding Learning |
| Authors | Meng Qu, Xiang Ren, Yu Zhang, Jiawei Han |
| Abstract | Extracting relations from text corpora is an important task in text mining. It becomes particularly challenging when focusing on weakly-supervised relation extraction, that is, utilizing a few relation instances (i.e., a pair of entities and their relation) as seeds to extract more instances from corpora. Existing distributional approaches leverage the corpus-level co-occurrence statistics of entities to predict their relations, and require large number of labeled instances to learn effective relation classifiers. Alternatively, pattern-based approaches perform bootstrapping or apply neural networks to model the local contexts, but still rely on large number of labeled instances to build reliable models. In this paper, we study integrating the distributional and pattern-based methods in a weakly-supervised setting, such that the two types of methods can provide complementary supervision for each other to build an effective, unified model. We propose a novel co-training framework with a distributional module and a pattern module. During training, the distributional module helps the pattern module discriminate between the informative patterns and other patterns, and the pattern module generates some highly-confident instances to improve the distributional module. The whole framework can be effectively optimized by iterating between improving the pattern module and updating the distributional module. We conduct experiments on two tasks: knowledge base completion with text corpora and corpus-level relation extraction. Experimental results prove the effectiveness of our framework in the weakly-supervised setting. |
| Tasks | Knowledge Base Completion, Relation Extraction |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03226v2 |
| http://arxiv.org/pdf/1711.03226v2.pdf | |
| PWC | https://paperswithcode.com/paper/weakly-supervised-relation-extraction-by |
| Repo | |
| Framework | |
Disentangling Dynamics and Content for Control and Planning
| Title | Disentangling Dynamics and Content for Control and Planning |
| Authors | Ershad Banijamali, Ahmad Khajenezhad, Ali Ghodsi, Mohammad Ghavamzadeh |
| Abstract | In this paper, We study the problem of learning a controllable representation for high-dimensional observations of dynamical systems. Specifically, we consider a situation where there are multiple sets of observations of dynamical systems with identical underlying dynamics. Only one of these sets has information about the effect of actions on the observation and the rest are just some random observations of the system. Our goal is to utilize the information in that one set and find a representation for the other sets that can be used for planning and ling-term prediction. |
| Tasks | |
| Published | 2017-11-24 |
| URL | http://arxiv.org/abs/1711.09165v1 |
| http://arxiv.org/pdf/1711.09165v1.pdf | |
| PWC | https://paperswithcode.com/paper/disentangling-dynamics-and-content-for |
| Repo | |
| Framework | |
A strong converse bound for multiple hypothesis testing, with applications to high-dimensional estimation
| Title | A strong converse bound for multiple hypothesis testing, with applications to high-dimensional estimation |
| Authors | Ramji Venkataramanan, Oliver Johnson |
| Abstract | In statistical inference problems, we wish to obtain lower bounds on the minimax risk, that is to bound the performance of any possible estimator. A standard technique to obtain risk lower bounds involves the use of Fano’s inequality. In an information-theoretic setting, it is known that Fano’s inequality typically does not give a sharp converse result (error lower bound) for channel coding problems. Moreover, recent work has shown that an argument based on binary hypothesis testing gives tighter results. We adapt this technique to the statistical setting, and argue that Fano’s inequality can always be replaced by this approach to obtain tighter lower bounds that can be easily computed and are asymptotically sharp. We illustrate our technique in three applications: density estimation, active learning of a binary classifier, and compressed sensing, obtaining tighter risk lower bounds in each case. |
| Tasks | Active Learning, Density Estimation |
| Published | 2017-06-14 |
| URL | http://arxiv.org/abs/1706.04410v3 |
| http://arxiv.org/pdf/1706.04410v3.pdf | |
| PWC | https://paperswithcode.com/paper/a-strong-converse-bound-for-multiple |
| Repo | |
| Framework | |
Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data
| Title | Fixed-Rank Approximation of a Positive-Semidefinite Matrix from Streaming Data |
| Authors | Joel A. Tropp, Alp Yurtsever, Madeleine Udell, Volkan Cevher |
| Abstract | Several important applications, such as streaming PCA and semidefinite programming, involve a large-scale positive-semidefinite (psd) matrix that is presented as a sequence of linear updates. Because of storage limitations, it may only be possible to retain a sketch of the psd matrix. This paper develops a new algorithm for fixed-rank psd approximation from a sketch. The approach combines the Nystrom approximation with a novel mechanism for rank truncation. Theoretical analysis establishes that the proposed method can achieve any prescribed relative error in the Schatten 1-norm and that it exploits the spectral decay of the input matrix. Computer experiments show that the proposed method dominates alternative techniques for fixed-rank psd matrix approximation across a wide range of examples. |
| Tasks | |
| Published | 2017-06-18 |
| URL | http://arxiv.org/abs/1706.05736v1 |
| http://arxiv.org/pdf/1706.05736v1.pdf | |
| PWC | https://paperswithcode.com/paper/fixed-rank-approximation-of-a-positive |
| Repo | |
| Framework | |
Diving Deep into Clickbaits: Who Use Them to What Extents in Which Topics with What Effects?
| Title | Diving Deep into Clickbaits: Who Use Them to What Extents in Which Topics with What Effects? |
| Authors | Md Main Uddin Rony, Naeemul Hassan, Mohammad Yousuf |
| Abstract | The use of alluring headlines (clickbait) to tempt the readers has become a growing practice nowadays. For the sake of existence in the highly competitive media industry, most of the on-line media including the mainstream ones, have started following this practice. Although the wide-spread practice of clickbait makes the reader’s reliability on media vulnerable, a large scale analysis to reveal this fact is still absent. In this paper, we analyze 1.67 million Facebook posts created by 153 media organizations to understand the extent of clickbait practice, its impact and user engagement by using our own developed clickbait detection model. The model uses distributed sub-word embeddings learned from a large corpus. The accuracy of the model is 98.3%. Powered with this model, we further study the distribution of topics in clickbait and non-clickbait contents. |
| Tasks | Clickbait Detection, Word Embeddings |
| Published | 2017-03-28 |
| URL | http://arxiv.org/abs/1703.09400v1 |
| http://arxiv.org/pdf/1703.09400v1.pdf | |
| PWC | https://paperswithcode.com/paper/diving-deep-into-clickbaits-who-use-them-to |
| Repo | |
| Framework | |
BanglaLekha-Isolated: A Comprehensive Bangla Handwritten Character Dataset
| Title | BanglaLekha-Isolated: A Comprehensive Bangla Handwritten Character Dataset |
| Authors | Mithun Biswas, Rafiqul Islam, Gautam Kumar Shom, Md Shopon, Nabeel Mohammed, Sifat Momen, Md Anowarul Abedin |
| Abstract | Bangla handwriting recognition is becoming a very important issue nowadays. It is potentially a very important task specially for Bangla speaking population of Bangladesh and West Bengal. By keeping that in our mind we are introducing a comprehensive Bangla handwritten character dataset named BanglaLekha-Isolated. This dataset contains Bangla handwritten numerals, basic characters and compound characters. This dataset was collected from multiple geographical location within Bangladesh and includes sample collected from a variety of aged groups. This dataset can also be used for other classification problems i.e: gender, age, district. This is the largest dataset on Bangla handwritten characters yet. |
| Tasks | |
| Published | 2017-02-22 |
| URL | http://arxiv.org/abs/1703.10661v1 |
| http://arxiv.org/pdf/1703.10661v1.pdf | |
| PWC | https://paperswithcode.com/paper/banglalekha-isolated-a-comprehensive-bangla |
| Repo | |
| Framework | |
Does Phase Matter For Monaural Source Separation?
| Title | Does Phase Matter For Monaural Source Separation? |
| Authors | Mohit Dubey, Garrett Kenyon, Nils Carlson, Austin Thresher |
| Abstract | The “cocktail party” problem of fully separating multiple sources from a single channel audio waveform remains unsolved. Current biological understanding of neural encoding suggests that phase information is preserved and utilized at every stage of the auditory pathway. However, current computational approaches primarily discard phase information in order to mask amplitude spectrograms of sound. In this paper, we seek to address whether preserving phase information in spectral representations of sound provides better results in monaural separation of vocals from a musical track by using a neurally plausible sparse generative model. Our results demonstrate that preserving phase information reduces artifacts in the separated tracks, as quantified by the signal to artifact ratio (GSAR). Furthermore, our proposed method achieves state-of-the-art performance for source separation, as quantified by a mean signal to interference ratio (GSIR) of 19.46. |
| Tasks | |
| Published | 2017-11-02 |
| URL | http://arxiv.org/abs/1711.00913v1 |
| http://arxiv.org/pdf/1711.00913v1.pdf | |
| PWC | https://paperswithcode.com/paper/does-phase-matter-for-monaural-source |
| Repo | |
| Framework | |
