Paper Group ANR 242
Discriminative Block-Diagonal Representation Learning for Image Recognition. Learning Correspondence Structures for Person Re-identification. Uncovering Group Level Insights with Accordant Clustering. SparseNN: An Energy-Efficient Neural Network Accelerator Exploiting Input and Output Sparsity. On the convergence properties of a $K$-step averaging …
Discriminative Block-Diagonal Representation Learning for Image Recognition
| Title | Discriminative Block-Diagonal Representation Learning for Image Recognition |
| Authors | Zheng Zhang, Yong Xu, Ling Shao, Jian Yang |
| Abstract | Existing block-diagonal representation researches mainly focuses on casting block-diagonal regularization on training data, while only little attention is dedicated to concurrently learning both block-diagonal representations of training and test data. In this paper, we propose a discriminative block-diagonal low-rank representation (BDLRR) method for recognition. In particular, the elaborate BDLRR is formulated as a joint optimization problem of shrinking the unfavorable representation from off-block-diagonal elements and strengthening the compact block-diagonal representation under the semi-supervised framework of low-rank representation. To this end, we first impose penalty constraints on the negative representation to eliminate the correlation between different classes such that the incoherence criterion of the extra-class representation is boosted. Moreover, a constructed subspace model is developed to enhance the self-expressive power of training samples and further build the representation bridge between the training and test samples, such that the coherence of the learned intra-class representation is consistently heightened. Finally, the resulting optimization problem is solved elegantly by employing an alternative optimization strategy, and a simple recognition algorithm on the learned representation is utilized for final prediction. Extensive experimental results demonstrate that the proposed method achieves superb recognition results on four face image datasets, three character datasets, and the fifteen scene multi-categories dataset. It not only shows superior potential on image recognition but also outperforms state-of-the-art methods. |
| Tasks | Representation Learning |
| Published | 2017-07-12 |
| URL | http://arxiv.org/abs/1707.03548v1 |
| http://arxiv.org/pdf/1707.03548v1.pdf | |
| PWC | https://paperswithcode.com/paper/discriminative-block-diagonal-representation |
| Repo | |
| Framework | |
Learning Correspondence Structures for Person Re-identification
| Title | Learning Correspondence Structures for Person Re-identification |
| Authors | Weiyao Lin, Yang Shen, Junchi Yan, Mingliang Xu, Jianxin Wu, Jingdong Wang, Ke Lu |
| Abstract | This paper addresses the problem of handling spatial misalignments due to camera-view changes or human-pose variations in person re-identification. We first introduce a boosting-based approach to learn a correspondence structure which indicates the patch-wise matching probabilities between images from a target camera pair. The learned correspondence structure can not only capture the spatial correspondence pattern between cameras but also handle the viewpoint or human-pose variation in individual images. We further introduce a global constraint-based matching process. It integrates a global matching constraint over the learned correspondence structure to exclude cross-view misalignments during the image patch matching process, hence achieving a more reliable matching score between images. Finally, we also extend our approach by introducing a multi-structure scheme, which learns a set of local correspondence structures to capture the spatial correspondence sub-patterns between a camera pair, so as to handle the spatial misalignments between individual images in a more precise way. Experimental results on various datasets demonstrate the effectiveness of our approach. |
| Tasks | Person Re-Identification |
| Published | 2017-03-20 |
| URL | http://arxiv.org/abs/1703.06931v3 |
| http://arxiv.org/pdf/1703.06931v3.pdf | |
| PWC | https://paperswithcode.com/paper/learning-correspondence-structures-for-person |
| Repo | |
| Framework | |
Uncovering Group Level Insights with Accordant Clustering
| Title | Uncovering Group Level Insights with Accordant Clustering |
| Authors | Amit Dhurandhar, Margareta Ackerman, Xiang Wang |
| Abstract | Clustering is a widely-used data mining tool, which aims to discover partitions of similar items in data. We introduce a new clustering paradigm, \emph{accordant clustering}, which enables the discovery of (predefined) group level insights. Unlike previous clustering paradigms that aim to understand relationships amongst the individual members, the goal of accordant clustering is to uncover insights at the group level through the analysis of their members. Group level insight can often support a call to action that cannot be informed through previous clustering techniques. We propose the first accordant clustering algorithm, and prove that it finds near-optimal solutions when data possesses inherent cluster structure. The insights revealed by accordant clusterings enabled experts in the field of medicine to isolate successful treatments for a neurodegenerative disease, and those in finance to discover patterns of unnecessary spending. |
| Tasks | |
| Published | 2017-04-07 |
| URL | http://arxiv.org/abs/1704.02378v1 |
| http://arxiv.org/pdf/1704.02378v1.pdf | |
| PWC | https://paperswithcode.com/paper/uncovering-group-level-insights-with |
| Repo | |
| Framework | |
SparseNN: An Energy-Efficient Neural Network Accelerator Exploiting Input and Output Sparsity
| Title | SparseNN: An Energy-Efficient Neural Network Accelerator Exploiting Input and Output Sparsity |
| Authors | Jingyang Zhu, Jingbo Jiang, Xizi Chen, Chi-Ying Tsui |
| Abstract | Contemporary Deep Neural Network (DNN) contains millions of synaptic connections with tens to hundreds of layers. The large computation and memory requirements pose a challenge to the hardware design. In this work, we leverage the intrinsic activation sparsity of DNN to substantially reduce the execution cycles and the energy consumption. An end-to-end training algorithm is proposed to develop a lightweight run-time predictor for the output activation sparsity on the fly. From our experimental results, the computation overhead of the prediction phase can be reduced to less than 5% of the original feedforward phase with negligible accuracy loss. Furthermore, an energy-efficient hardware architecture, SparseNN, is proposed to exploit both the input and output sparsity. SparseNN is a scalable architecture with distributed memories and processing elements connected through a dedicated on-chip network. Compared with the state-of-the-art accelerators which only exploit the input sparsity, SparseNN can achieve a 10%-70% improvement in throughput and a power reduction of around 50%. |
| Tasks | |
| Published | 2017-11-03 |
| URL | http://arxiv.org/abs/1711.01263v1 |
| http://arxiv.org/pdf/1711.01263v1.pdf | |
| PWC | https://paperswithcode.com/paper/sparsenn-an-energy-efficient-neural-network |
| Repo | |
| Framework | |
On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization
| Title | On the convergence properties of a $K$-step averaging stochastic gradient descent algorithm for nonconvex optimization |
| Authors | Fan Zhou, Guojing Cong |
| Abstract | Despite their popularity, the practical performance of asynchronous stochastic gradient descent methods (ASGD) for solving large scale machine learning problems are not as good as theoretical results indicate. We adopt and analyze a synchronous K-step averaging stochastic gradient descent algorithm which we call K-AVG. We establish the convergence results of K-AVG for nonconvex objectives and explain why the K-step delay is necessary and leads to better performance than traditional parallel stochastic gradient descent which is a special case of K-AVG with $K=1$. We also show that K-AVG scales better than ASGD. Another advantage of K-AVG over ASGD is that it allows larger stepsizes. On a cluster of $128$ GPUs, K-AVG is faster than ASGD implementations and achieves better accuracies and faster convergence for \cifar dataset. |
| Tasks | |
| Published | 2017-08-03 |
| URL | http://arxiv.org/abs/1708.01012v3 |
| http://arxiv.org/pdf/1708.01012v3.pdf | |
| PWC | https://paperswithcode.com/paper/on-the-convergence-properties-of-a-k-step |
| Repo | |
| Framework | |
Machine Learning in Appearance-based Robot Self-localization
| Title | Machine Learning in Appearance-based Robot Self-localization |
| Authors | Alexander Kuleshov, Alexander Bernstein, Evgeny Burnaev, Yury Yanovich |
| Abstract | An appearance-based robot self-localization problem is considered in the machine learning framework. The appearance space is composed of all possible images, which can be captured by a robot’s visual system under all robot localizations. Using recent manifold learning and deep learning techniques, we propose a new geometrically motivated solution based on training data consisting of a finite set of images captured in known locations of the robot. The solution includes estimation of the robot localization mapping from the appearance space to the robot localization space, as well as estimation of the inverse mapping for modeling visual image features. The latter allows solving the robot localization problem as the Kalman filtering problem. |
| Tasks | |
| Published | 2017-06-17 |
| URL | http://arxiv.org/abs/1707.03469v2 |
| http://arxiv.org/pdf/1707.03469v2.pdf | |
| PWC | https://paperswithcode.com/paper/machine-learning-in-appearance-based-robot |
| Repo | |
| Framework | |
Learning to Draw Samples with Amortized Stein Variational Gradient Descent
| Title | Learning to Draw Samples with Amortized Stein Variational Gradient Descent |
| Authors | Yihao Feng, Dilin Wang, Qiang Liu |
| Abstract | We propose a simple algorithm to train stochastic neural networks to draw samples from given target distributions for probabilistic inference. Our method is based on iteratively adjusting the neural network parameters so that the output changes along a Stein variational gradient direction (Liu & Wang, 2016) that maximally decreases the KL divergence with the target distribution. Our method works for any target distribution specified by their unnormalized density function, and can train any black-box architectures that are differentiable in terms of the parameters we want to adapt. We demonstrate our method with a number of applications, including variational autoencoder (VAE) with expressive encoders to model complex latent space structures, and hyper-parameter learning of MCMC samplers that allows Bayesian inference to adaptively improve itself when seeing more data. |
| Tasks | Bayesian Inference |
| Published | 2017-07-20 |
| URL | http://arxiv.org/abs/1707.06626v2 |
| http://arxiv.org/pdf/1707.06626v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-to-draw-samples-with-amortized-stein |
| Repo | |
| Framework | |
Assortment Optimization under Unknown MultiNomial Logit Choice Models
| Title | Assortment Optimization under Unknown MultiNomial Logit Choice Models |
| Authors | Wang Chi Cheung, David Simchi-Levi |
| Abstract | Motivated by e-commerce, we study the online assortment optimization problem. The seller offers an assortment, i.e. a subset of products, to each arriving customer, who then purchases one or no product from her offered assortment. A customer’s purchase decision is governed by the underlying MultiNomial Logit (MNL) choice model. The seller aims to maximize the total revenue in a finite sales horizon, subject to resource constraints and uncertainty in the MNL choice model. We first propose an efficient online policy which incurs a regret $\tilde{O}(T^{2/3})$, where $T$ is the number of customers in the sales horizon. Then, we propose a UCB policy that achieves a regret $\tilde{O}(T^{1/2})$. Both regret bounds are sublinear in the number of assortments. |
| Tasks | |
| Published | 2017-04-01 |
| URL | http://arxiv.org/abs/1704.00108v1 |
| http://arxiv.org/pdf/1704.00108v1.pdf | |
| PWC | https://paperswithcode.com/paper/assortment-optimization-under-unknown |
| Repo | |
| Framework | |
Hierarchical Salient Object Detection for Assisted Grasping
| Title | Hierarchical Salient Object Detection for Assisted Grasping |
| Authors | Dominik Alexander Klein, Boris Illing, Bastian Gaspers, Dirk Schulz, Armin Bernd Cremers |
| Abstract | Visual scene decomposition into semantic entities is one of the major challenges when creating a reliable object grasping system. Recently, we introduced a bottom-up hierarchical clustering approach which is able to segment objects and parts in a scene. In this paper, we introduce a transform from such a segmentation into a corresponding, hierarchical saliency function. In comprehensive experiments we demonstrate its ability to detect salient objects in a scene. Furthermore, this hierarchical saliency defines a most salient corresponding region (scale) for every point in an image. Based on this, an easy-to-use pick and place manipulation system was developed and tested exemplarily. |
| Tasks | Object Detection, Salient Object Detection |
| Published | 2017-01-16 |
| URL | http://arxiv.org/abs/1701.04284v2 |
| http://arxiv.org/pdf/1701.04284v2.pdf | |
| PWC | https://paperswithcode.com/paper/hierarchical-salient-object-detection-for |
| Repo | |
| Framework | |
Clustering Semi-Random Mixtures of Gaussians
| Title | Clustering Semi-Random Mixtures of Gaussians |
| Authors | Pranjal Awasthi, Aravindan Vijayaraghavan |
| Abstract | Gaussian mixture models (GMM) are the most widely used statistical model for the $k$-means clustering problem and form a popular framework for clustering in machine learning and data analysis. In this paper, we propose a natural semi-random model for $k$-means clustering that generalizes the Gaussian mixture model, and that we believe will be useful in identifying robust algorithms. In our model, a semi-random adversary is allowed to make arbitrary “monotone” or helpful changes to the data generated from the Gaussian mixture model. Our first contribution is a polynomial time algorithm that provably recovers the ground-truth up to small classification error w.h.p., assuming certain separation between the components. Perhaps surprisingly, the algorithm we analyze is the popular Lloyd’s algorithm for $k$-means clustering that is the method-of-choice in practice. Our second result complements the upper bound by giving a nearly matching information-theoretic lower bound on the number of misclassified points incurred by any $k$-means clustering algorithm on the semi-random model. |
| Tasks | |
| Published | 2017-11-23 |
| URL | http://arxiv.org/abs/1711.08841v1 |
| http://arxiv.org/pdf/1711.08841v1.pdf | |
| PWC | https://paperswithcode.com/paper/clustering-semi-random-mixtures-of-gaussians |
| Repo | |
| Framework | |
Deep Learning as a Tool to Predict Flow Patterns in Two-Phase Flow
| Title | Deep Learning as a Tool to Predict Flow Patterns in Two-Phase Flow |
| Authors | Mohammadmehdi Ezzatabadipour, Parth Singh, Melvin D. Robinson, Pablo Guillen-Rondon, Carlos Torres |
| Abstract | In order to better model complex real-world data such as multiphase flow, one approach is to develop pattern recognition techniques and robust features that capture the relevant information. In this paper, we use deep learning methods, and in particular employ the multilayer perceptron, to build an algorithm that can predict flow pattern in twophase flow from fluid properties and pipe conditions. The preliminary results show excellent performance when compared with classical methods of flow pattern prediction. |
| Tasks | |
| Published | 2017-05-19 |
| URL | http://arxiv.org/abs/1705.07117v1 |
| http://arxiv.org/pdf/1705.07117v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-learning-as-a-tool-to-predict-flow |
| Repo | |
| Framework | |
Tensor Valued Common and Individual Feature Extraction: Multi-dimensional Perspective
| Title | Tensor Valued Common and Individual Feature Extraction: Multi-dimensional Perspective |
| Authors | Ilia Kisil, Giuseppe G. Calvi, Danilo P. Mandic |
| Abstract | A novel method for common and individual feature analysis from exceedingly large-scale data is proposed, in order to ensure the tractability of both the computation and storage and thus mitigate the curse of dimensionality, a major bottleneck in modern data science. This is achieved by making use of the inherent redundancy in so-called multi-block data structures, which represent multiple observations of the same phenomenon taken at different times, angles or recording conditions. Upon providing an intrinsic link between the properties of the outer vector product and extracted features in tensor decompositions (TDs), the proposed common and individual information extraction from multi-block data is performed through imposing physical meaning to otherwise unconstrained factorisation approaches. This is shown to dramatically reduce the dimensionality of search spaces for subsequent classification procedures and to yield greatly enhanced accuracy. Simulations on a multi-class classification task of large-scale extraction of individual features from a collection of partially related real-world images demonstrate the advantages of the “blessing of dimensionality” associated with TDs. |
| Tasks | |
| Published | 2017-11-01 |
| URL | http://arxiv.org/abs/1711.00487v1 |
| http://arxiv.org/pdf/1711.00487v1.pdf | |
| PWC | https://paperswithcode.com/paper/tensor-valued-common-and-individual-feature |
| Repo | |
| Framework | |
Multiband NFC for High-Throughput Wireless Computer Vision Sensor Network
| Title | Multiband NFC for High-Throughput Wireless Computer Vision Sensor Network |
| Authors | F. Li, J. Du |
| Abstract | Vision sensors lie in the heart of computer vision. In many computer vision applications, such as AR/VR, non-contacting near-field communication (NFC) with high throughput is required to transfer information to algorithms. In this work, we proposed a novel NFC system which utilizes multiple frequency bands to achieve high throughput. |
| Tasks | |
| Published | 2017-05-28 |
| URL | http://arxiv.org/abs/1707.03720v1 |
| http://arxiv.org/pdf/1707.03720v1.pdf | |
| PWC | https://paperswithcode.com/paper/multiband-nfc-for-high-throughput-wireless |
| Repo | |
| Framework | |
Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks
| Title | Unsupervised Visual Attribute Transfer with Reconfigurable Generative Adversarial Networks |
| Authors | Taeksoo Kim, Byoungjip Kim, Moonsu Cha, Jiwon Kim |
| Abstract | Learning to transfer visual attributes requires supervision dataset. Corresponding images with varying attribute values with the same identity are required for learning the transfer function. This largely limits their applications, because capturing them is often a difficult task. To address the issue, we propose an unsupervised method to learn to transfer visual attribute. The proposed method can learn the transfer function without any corresponding images. Inspecting visualization results from various unsupervised attribute transfer tasks, we verify the effectiveness of the proposed method. |
| Tasks | |
| Published | 2017-07-31 |
| URL | http://arxiv.org/abs/1707.09798v1 |
| http://arxiv.org/pdf/1707.09798v1.pdf | |
| PWC | https://paperswithcode.com/paper/unsupervised-visual-attribute-transfer-with |
| Repo | |
| Framework | |
Spatial PixelCNN: Generating Images from Patches
| Title | Spatial PixelCNN: Generating Images from Patches |
| Authors | Nader Akoury, Anh Nguyen |
| Abstract | In this paper we propose Spatial PixelCNN, a conditional autoregressive model that generates images from small patches. By conditioning on a grid of pixel coordinates and global features extracted from a Variational Autoencoder (VAE), we are able to train on patches of images, and reproduce the full-sized image. We show that it not only allows for generating high quality samples at the same resolution as the underlying dataset, but is also capable of upscaling images to arbitrary resolutions (tested at resolutions up to $50\times$) on the MNIST dataset. Compared to a PixelCNN++ baseline, Spatial PixelCNN quantitatively and qualitatively achieves similar performance on the MNIST dataset. |
| Tasks | |
| Published | 2017-12-03 |
| URL | http://arxiv.org/abs/1712.00714v1 |
| http://arxiv.org/pdf/1712.00714v1.pdf | |
| PWC | https://paperswithcode.com/paper/spatial-pixelcnn-generating-images-from |
| Repo | |
| Framework | |
