Paper Group ANR 497
Stochastic Non-convex Optimization with Strong High Probability Second-order Convergence. An Ensemble Classification Algorithm Based on Information Entropy for Data Streams. Adversarial Multi-task Learning for Text Classification. Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks. HSC: A Novel Method for Clustering Hierar …
Stochastic Non-convex Optimization with Strong High Probability Second-order Convergence
| Title | Stochastic Non-convex Optimization with Strong High Probability Second-order Convergence |
| Authors | Mingrui Liu, Tianbao Yang |
| Abstract | In this paper, we study stochastic non-convex optimization with non-convex random functions. Recent studies on non-convex optimization revolve around establishing second-order convergence, i.e., converging to a nearly second-order optimal stationary points. However, existing results on stochastic non-convex optimization are limited, especially with a high probability second-order convergence. We propose a novel updating step (named NCG-S) by leveraging a stochastic gradient and a noisy negative curvature of a stochastic Hessian, where the stochastic gradient and Hessian are based on a proper mini-batch of random functions. Building on this step, we develop two algorithms and establish their high probability second-order convergence. To the best of our knowledge, the proposed stochastic algorithms are the first with a second-order convergence in {\it high probability} and a time complexity that is {\it almost linear} in the problem’s dimensionality. |
| Tasks | |
| Published | 2017-10-25 |
| URL | http://arxiv.org/abs/1710.09447v2 |
| http://arxiv.org/pdf/1710.09447v2.pdf | |
| PWC | https://paperswithcode.com/paper/stochastic-non-convex-optimization-with |
| Repo | |
| Framework | |
An Ensemble Classification Algorithm Based on Information Entropy for Data Streams
| Title | An Ensemble Classification Algorithm Based on Information Entropy for Data Streams |
| Authors | Junhong Wang, Shuliang Xu, Bingqian Duan, Caifeng Liu, Jiye Liang |
| Abstract | Data stream mining problem has caused widely concerns in the area of machine learning and data mining. In some recent studies, ensemble classification has been widely used in concept drift detection, however, most of them regard classification accuracy as a criterion for judging whether concept drift happening or not. Information entropy is an important and effective method for measuring uncertainty. Based on the information entropy theory, a new algorithm using information entropy to evaluate a classification result is developed. It uses ensemble classification techniques, and the weight of each classifier is decided through the entropy of the result produced by an ensemble classifiers system. When the concept in data streams changing, the classifiers’ weight below a threshold value will be abandoned to adapt to a new concept in one time. In the experimental analysis section, six databases and four proposed algorithms are executed. The results show that the proposed method can not only handle concept drift effectively, but also have a better classification accuracy and time performance than the contrastive algorithms. |
| Tasks | |
| Published | 2017-08-11 |
| URL | http://arxiv.org/abs/1708.03496v1 |
| http://arxiv.org/pdf/1708.03496v1.pdf | |
| PWC | https://paperswithcode.com/paper/an-ensemble-classification-algorithm-based-on |
| Repo | |
| Framework | |
Adversarial Multi-task Learning for Text Classification
| Title | Adversarial Multi-task Learning for Text Classification |
| Authors | Pengfei Liu, Xipeng Qiu, Xuanjing Huang |
| Abstract | Neural network models have shown their promising opportunities for multi-task learning, which focus on learning the shared layers to extract the common and task-invariant features. However, in most existing approaches, the extracted shared features are prone to be contaminated by task-specific features or the noise brought by other tasks. In this paper, we propose an adversarial multi-task learning framework, alleviating the shared and private latent feature spaces from interfering with each other. We conduct extensive experiments on 16 different text classification tasks, which demonstrates the benefits of our approach. Besides, we show that the shared knowledge learned by our proposed model can be regarded as off-the-shelf knowledge and easily transferred to new tasks. The datasets of all 16 tasks are publicly available at \url{http://nlp.fudan.edu.cn/data/} |
| Tasks | Multi-Task Learning, Text Classification |
| Published | 2017-04-19 |
| URL | http://arxiv.org/abs/1704.05742v1 |
| http://arxiv.org/pdf/1704.05742v1.pdf | |
| PWC | https://paperswithcode.com/paper/adversarial-multi-task-learning-for-text |
| Repo | |
| Framework | |
Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks
| Title | Deep Reinforcement Learning for Dexterous Manipulation with Concept Networks |
| Authors | Aditya Gudimella, Ross Story, Matineh Shaker, Ruofan Kong, Matthew Brown, Victor Shnayder, Marcos Campos |
| Abstract | Deep reinforcement learning yields great results for a large array of problems, but models are generally retrained anew for each new problem to be solved. Prior learning and knowledge are difficult to incorporate when training new models, requiring increasingly longer training as problems become more complex. This is especially problematic for problems with sparse rewards. We provide a solution to these problems by introducing Concept Network Reinforcement Learning (CNRL), a framework which allows us to decompose problems using a multi-level hierarchy. Concepts in a concept network are reusable, and flexible enough to encapsulate feature extractors, skills, or other concept networks. With this hierarchical learning approach, deep reinforcement learning can be used to solve complex tasks in a modular way, through problem decomposition. We demonstrate the strength of CNRL by training a model to grasp a rectangular prism and precisely stack it on top of a cube using a gripper on a Kinova JACO arm, simulated in MuJoCo. Our experiments show that our use of hierarchy results in a 45x reduction in environment interactions compared to the state-of-the-art on this task. |
| Tasks | Problem Decomposition |
| Published | 2017-09-20 |
| URL | http://arxiv.org/abs/1709.06977v1 |
| http://arxiv.org/pdf/1709.06977v1.pdf | |
| PWC | https://paperswithcode.com/paper/deep-reinforcement-learning-for-dexterous |
| Repo | |
| Framework | |
HSC: A Novel Method for Clustering Hierarchies of Networked Data
| Title | HSC: A Novel Method for Clustering Hierarchies of Networked Data |
| Authors | Antonia Korba |
| Abstract | Hierarchical clustering is one of the most powerful solutions to the problem of clustering, on the grounds that it performs a multi scale organization of the data. In recent years, research on hierarchical clustering methods has attracted considerable interest due to the demanding modern application domains. We present a novel divisive hierarchical clustering framework called Hierarchical Stochastic Clustering (HSC), that acts in two stages. In the first stage, it finds a primary hierarchy of clustering partitions in a dataset. In the second stage, feeds a clustering algorithm with each one of the clusters of the very detailed partition, in order to settle the final result. The output is a hierarchy of clusters. Our method is based on the previous research of Meyer and Weissel Stochastic Data Clustering and the theory of Simon and Ando on Variable Aggregation. Our experiments show that our framework builds a meaningful hierarchy of clusters and benefits consistently the clustering algorithm that acts in the second stage, not only computationally but also in terms of cluster quality. This result suggest that HSC framework is ideal for obtaining hierarchical solutions of large volumes of data. |
| Tasks | |
| Published | 2017-11-29 |
| URL | https://arxiv.org/abs/1711.11071v2 |
| https://arxiv.org/pdf/1711.11071v2.pdf | |
| PWC | https://paperswithcode.com/paper/hsc-a-novel-method-for-clustering-hierarchies |
| Repo | |
| Framework | |
Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds
| Title | Learning a Robust Representation via a Deep Network on Symmetric Positive Definite Manifolds |
| Authors | Zhi Gao, Yuwei Wu, Xingyuan Bu, Yunde Jia |
| Abstract | Recent studies have shown that aggregating convolutional features of a pre-trained Convolutional Neural Network (CNN) can obtain impressive performance for a variety of visual tasks. The symmetric Positive Definite (SPD) matrix becomes a powerful tool due to its remarkable ability to learn an appropriate statistic representation to characterize the underlying structure of visual features. In this paper, we propose to aggregate deep convolutional features into an SPD matrix representation through the SPD generation and the SPD transformation under an end-to-end deep network. To this end, several new layers are introduced in our network, including a nonlinear kernel aggregation layer, an SPD matrix transformation layer, and a vectorization layer. The nonlinear kernel aggregation layer is employed to aggregate the convolutional features into a real SPD matrix directly. The SPD matrix transformation layer is designed to construct a more compact and discriminative SPD representation. The vectorization and normalization operations are performed in the vectorization layer for reducing the redundancy and accelerating the convergence. The SPD matrix in our network can be considered as a mid-level representation bridging convolutional features and high-level semantic features. To demonstrate the effectiveness of our method, we conduct extensive experiments on visual classification. Experiment results show that our method notably outperforms state-of-the-art methods. |
| Tasks | |
| Published | 2017-11-17 |
| URL | http://arxiv.org/abs/1711.06540v2 |
| http://arxiv.org/pdf/1711.06540v2.pdf | |
| PWC | https://paperswithcode.com/paper/learning-a-robust-representation-via-a-deep |
| Repo | |
| Framework | |
Efficient Learning of Mixed Membership Models
| Title | Efficient Learning of Mixed Membership Models |
| Authors | Zilong Tan, Sayan Mukherjee |
| Abstract | We present an efficient algorithm for learning mixed membership models when the number of variables $p$ is much larger than the number of hidden components $k$. This algorithm reduces the computational complexity of state-of-the-art tensor methods, which require decomposing an $O\left(p^3\right)$ tensor, to factorizing $O\left(p/k\right)$ sub-tensors each of size $O\left(k^3\right)$. In addition, we address the issue of negative entries in the empirical method of moments based estimators. We provide sufficient conditions under which our approach has provable guarantees. Our approach obtains competitive empirical results on both simulated and real data. |
| Tasks | |
| Published | 2017-02-25 |
| URL | http://arxiv.org/abs/1702.07933v3 |
| http://arxiv.org/pdf/1702.07933v3.pdf | |
| PWC | https://paperswithcode.com/paper/efficient-learning-of-mixed-membership-models |
| Repo | |
| Framework | |
Toward Depth Estimation Using Mask-Based Lensless Cameras
| Title | Toward Depth Estimation Using Mask-Based Lensless Cameras |
| Authors | M. Salman Asif |
| Abstract | Recently, coded masks have been used to demonstrate a thin form-factor lensless camera, FlatCam, in which a mask is placed immediately on top of a bare image sensor. In this paper, we present an imaging model and algorithm to jointly estimate depth and intensity information in the scene from a single or multiple FlatCams. We use a light field representation to model the mapping of 3D scene onto the sensor in which light rays from different depths yield different modulation patterns. We present a greedy depth pursuit algorithm to search the 3D volume and estimate the depth and intensity of each pixel within the camera field-of-view. We present simulation results to analyze the performance of our proposed model and algorithm with different FlatCam settings. |
| Tasks | Depth Estimation |
| Published | 2017-11-09 |
| URL | http://arxiv.org/abs/1711.03527v1 |
| http://arxiv.org/pdf/1711.03527v1.pdf | |
| PWC | https://paperswithcode.com/paper/toward-depth-estimation-using-mask-based |
| Repo | |
| Framework | |
Automatic Dataset Augmentation
| Title | Automatic Dataset Augmentation |
| Authors | Yalong Bai, Kuiyuan Yang, Tao Mei, Wei-Ying Ma, Tiejun Zhao |
| Abstract | Large scale image dataset and deep convolutional neural network (DCNN) are two primary driving forces for the rapid progress made in generic object recognition tasks in recent years. While lots of network architectures have been continuously designed to pursue lower error rates, few efforts are devoted to enlarge existing datasets due to high labeling cost and unfair comparison issues. In this paper, we aim to achieve lower error rate by augmenting existing datasets in an automatic manner. Our method leverages both Web and DCNN, where Web provides massive images with rich contextual information, and DCNN replaces human to automatically label images under guidance of Web contextual information. Experiments show our method can automatically scale up existing datasets significantly from billions web pages with high accuracy, and significantly improve the performance on object recognition tasks by using the automatically augmented datasets, which demonstrates that more supervisory information has been automatically gathered from the Web. Both the dataset and models trained on the dataset are made publicly available. |
| Tasks | Object Recognition |
| Published | 2017-08-28 |
| URL | http://arxiv.org/abs/1708.08201v2 |
| http://arxiv.org/pdf/1708.08201v2.pdf | |
| PWC | https://paperswithcode.com/paper/automatic-dataset-augmentation |
| Repo | |
| Framework | |
Prior-based Hierarchical Segmentation Highlighting Structures of Interest
| Title | Prior-based Hierarchical Segmentation Highlighting Structures of Interest |
| Authors | Amin Fehri, Santiago Velasco-Forero, Fernand Meyer |
| Abstract | Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in this regard as it favors the emergence of important regions at different scales. On the other hand, many methods allow us to have prior information on the position of structures of interest in the images. In this paper, we present a versatile hierarchical segmentation method that takes into account any prior spatial information and outputs a hierarchical segmentation that emphasizes the contours or regions of interest while preserving the important structures in the image. Several applications are presented that illustrate the method versatility and efficiency. |
| Tasks | Semantic Segmentation |
| Published | 2017-03-09 |
| URL | http://arxiv.org/abs/1703.03196v1 |
| http://arxiv.org/pdf/1703.03196v1.pdf | |
| PWC | https://paperswithcode.com/paper/prior-based-hierarchical-segmentation |
| Repo | |
| Framework | |
iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects
| Title | iPose: Instance-Aware 6D Pose Estimation of Partly Occluded Objects |
| Authors | Omid Hosseini Jafari, Siva Karthik Mustikovela, Karl Pertsch, Eric Brachmann, Carsten Rother |
| Abstract | We address the task of 6D pose estimation of known rigid objects from single input images in scenarios where the objects are partly occluded. Recent RGB-D-based methods are robust to moderate degrees of occlusion. For RGB inputs, no previous method works well for partly occluded objects. Our main contribution is to present the first deep learning-based system that estimates accurate poses for partly occluded objects from RGB-D and RGB input. We achieve this with a new instance-aware pipeline that decomposes 6D object pose estimation into a sequence of simpler steps, where each step removes specific aspects of the problem. The first step localizes all known objects in the image using an instance segmentation network, and hence eliminates surrounding clutter and occluders. The second step densely maps pixels to 3D object surface positions, so called object coordinates, using an encoder-decoder network, and hence eliminates object appearance. The third, and final, step predicts the 6D pose using geometric optimization. We demonstrate that we significantly outperform the state-of-the-art for pose estimation of partly occluded objects for both RGB and RGB-D input. |
| Tasks | 6D Pose Estimation, 6D Pose Estimation using RGB, Instance Segmentation, Pose Estimation, Semantic Segmentation |
| Published | 2017-12-05 |
| URL | http://arxiv.org/abs/1712.01924v3 |
| http://arxiv.org/pdf/1712.01924v3.pdf | |
| PWC | https://paperswithcode.com/paper/ipose-instance-aware-6d-pose-estimation-of |
| Repo | |
| Framework | |
Divide and Fuse: A Re-ranking Approach for Person Re-identification
| Title | Divide and Fuse: A Re-ranking Approach for Person Re-identification |
| Authors | Rui Yu, Zhichao Zhou, Song Bai, Xiang Bai |
| Abstract | As re-ranking is a necessary procedure to boost person re-identification (re-ID) performance on large-scale datasets, the diversity of feature becomes crucial to person reID for its importance both on designing pedestrian descriptions and re-ranking based on feature fusion. However, in many circumstances, only one type of pedestrian feature is available. In this paper, we propose a “Divide and use” re-ranking framework for person re-ID. It exploits the diversity from different parts of a high-dimensional feature vector for fusion-based re-ranking, while no other features are accessible. Specifically, given an image, the extracted feature is divided into sub-features. Then the contextual information of each sub-feature is iteratively encoded into a new feature. Finally, the new features from the same image are fused into one vector for re-ranking. Experimental results on two person re-ID benchmarks demonstrate the effectiveness of the proposed framework. Especially, our method outperforms the state-of-the-art on the Market-1501 dataset. |
| Tasks | Person Re-Identification |
| Published | 2017-08-11 |
| URL | http://arxiv.org/abs/1708.04169v1 |
| http://arxiv.org/pdf/1708.04169v1.pdf | |
| PWC | https://paperswithcode.com/paper/divide-and-fuse-a-re-ranking-approach-for |
| Repo | |
| Framework | |
Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review
| Title | Deep convolutional neural networks for brain image analysis on magnetic resonance imaging: a review |
| Authors | Jose Bernal, Kaisar Kushibar, Daniel S. Asfaw, Sergi Valverde, Arnau Oliver, Robert Martí, Xavier Lladó |
| Abstract | In recent years, deep convolutional neural networks (CNNs) have shown record-shattering performance in a variety of computer vision problems, such as visual object recognition, detection and segmentation. These methods have also been utilised in medical image analysis domain for lesion segmentation, anatomical segmentation and classification. We present an extensive literature review of CNN techniques applied in brain magnetic resonance imaging (MRI) analysis, focusing on the architectures, pre-processing, data-preparation and post-processing strategies available in these works. The aim of this study is three-fold. Our primary goal is to report how different CNN architectures have evolved, discuss state-of-the-art strategies, condense their results obtained using public datasets and examine their pros and cons. Second, this paper is intended to be a detailed reference of the research activity in deep CNN for brain MRI analysis. Finally, we present a perspective on the future of CNNs in which we hint some of the research directions in subsequent years. |
| Tasks | Lesion Segmentation, Object Recognition |
| Published | 2017-12-11 |
| URL | http://arxiv.org/abs/1712.03747v3 |
| http://arxiv.org/pdf/1712.03747v3.pdf | |
| PWC | https://paperswithcode.com/paper/deep-convolutional-neural-networks-for-brain |
| Repo | |
| Framework | |
DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
| Title | DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics |
| Authors | Han Wang, Linfeng Zhang, Jiequn Han, Weinan E |
| Abstract | Recent developments in many-body potential energy representation via deep learning have brought new hopes to addressing the accuracy-versus-efficiency dilemma in molecular simulations. Here we describe DeePMD-kit, a package written in Python/C++ that has been designed to minimize the effort required to build deep learning based representation of potential energy and force field and to perform molecular dynamics. Potential applications of DeePMD-kit span from finite molecules to extended systems and from metallic systems to chemically bonded systems. DeePMD-kit is interfaced with TensorFlow, one of the most popular deep learning frameworks, making the training process highly automatic and efficient. On the other end, DeePMD-kit is interfaced with high-performance classical molecular dynamics and quantum (path-integral) molecular dynamics packages, i.e., LAMMPS and the i-PI, respectively. Thus, upon training, the potential energy and force field models can be used to perform efficient molecular simulations for different purposes. As an example of the many potential applications of the package, we use DeePMD-kit to learn the interatomic potential energy and forces of a water model using data obtained from density functional theory. We demonstrate that the resulted molecular dynamics model reproduces accurately the structural information contained in the original model. |
| Tasks | |
| Published | 2017-12-11 |
| URL | http://arxiv.org/abs/1712.03641v2 |
| http://arxiv.org/pdf/1712.03641v2.pdf | |
| PWC | https://paperswithcode.com/paper/deepmd-kit-a-deep-learning-package-for-many |
| Repo | |
| Framework | |
A fast nonconvex Compressed Sensing algorithm for highly low-sampled MR images reconstruction
| Title | A fast nonconvex Compressed Sensing algorithm for highly low-sampled MR images reconstruction |
| Authors | Damiana Lazzaro, Elena Loli Piccolomini, Fabiana Zama |
| Abstract | In this paper we present a fast and efficient method for the reconstruction of Magnetic Resonance Images (MRI) from severely under-sampled data. From the Compressed Sensing theory we have mathematically modeled the problem as a constrained minimization problem with a family of non-convex regularizing objective functions depending on a parameter and a least squares data fit constraint. We propose a fast and efficient algorithm, named Fast NonConvex Reweighting (FNCR) algorithm, based on an iterative scheme where the non-convex problem is approximated by its convex linearization and the penalization parameter is automatically updated. The convex problem is solved by a Forward-Backward procedure, where the Backward step is performed by a Split Bregman strategy. Moreover, we propose a new efficient iterative solver for the arising linear systems. We prove the convergence of the proposed FNCR method. The results on synthetic phantoms and real images show that the algorithm is very well performing and computationally efficient, even when compared to the best performing methods proposed in the literature. |
| Tasks | |
| Published | 2017-11-29 |
| URL | http://arxiv.org/abs/1711.11075v1 |
| http://arxiv.org/pdf/1711.11075v1.pdf | |
| PWC | https://paperswithcode.com/paper/a-fast-nonconvex-compressed-sensing-algorithm |
| Repo | |
| Framework | |
