首页/论文/2004.09197

arXiv 2004.091972020-04-20cs.CV

LSM: Learning Subspace Minimization for Low-level Vision

Simon Fraser University（西蒙菲莎大学）；Microsoft（微软）

Chengzhou Tang, Lu Yuan, Ping Tan

备注：: To be presented at CVPR2020

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

We study the energy minimization problem in low-level vision tasks from a novel perspective. We replace the heuristic regularization term with a learnable subspace constraint, and preserve the data term to exploit domain knowledge derived from the first principle of a task. This learning subspace minimization (LSM) framework unifies the network structures and the parameters for many low-level vision tasks, which allows us to train a single network for multiple tasks simultaneously with completely shared parameters, and even generalizes the trained network to an unseen task as long as its data term can be formulated. We demonstrate our LSM framework on four low-level tasks including interactive image segmentation, video segmentation, stereo matching, and optical flow, and validate the network on various datasets. The experiments show that the proposed LSM generates state-of-the-art results with smaller model size, faster training convergence, and real-time inference.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Moving Object Detection in Video Using Saliency Map and Subspace Learning

Tianjin University（天津大学）；Institute of Optics and Precision Mechanics, Chinese Academy of Sciences（中国科学院西安光学精密机械研究所）

Moving object detection is a key to intelligent video analysis. On the one hand, what moves is not only interesting objects but also noise and cluttered background. On the other hand, moving objects without rich texture are prone not to be detected. So there are undesirable false alarms and missed alarms in many algorithms of moving object detection. To reduce the false alarms and missed alarms, in this paper, we propose to incorporate a saliency map into an incremental subspace analysis framework where the saliency map makes estimated background has less chance than foreground (i.e., moving o…

2015-09-30cs.CV

Constrained Low-Rank Learning Using Least Squares-Based Regularization

Low-rank learning has attracted much attention recently due to its efficacy in a rich variety of real-world tasks, e.g., subspace segmentation and image categorization. Most low-rank methods are incapable of capturing low-dimensional subspace for supervised learning tasks, e.g., classification and regression. This paper aims to learn both the discriminant low-rank representation (LRR) and the robust projecting subspace in a supervised manner. To achieve this goal, we cast the problem into a constrained rank minimization framework by adopting the least squares regularization. Naturally, the dat…

2016-11-15cs.CVcs.LG

Subspace clustering based on low rank representation and weighted nuclear norm minimization

Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；Nanjing Hydraulic Research Institute（南京水利科学研究院）；State Key Laboratory of Urban Water Resource and Environment（城市水资源与水环境国家重点实验室）；The Key Laboratory of Rivers and Lakes Governance and Flood Protection of Yangtse River Water Conservancy Committee（长江水利委员会江湖治理与防洪重点实验室）

Subspace clustering refers to the problem of segmenting a set of data points approximately drawn from a union of multiple linear subspaces. Aiming at the subspace clustering problem, various subspace clustering algorithms have been proposed and low rank representation based subspace clustering is a very promising and efficient subspace clustering algorithm. Low rank representation method seeks the lowest rank representation among all the candidates that can represent the data points as linear combinations of the bases in a given dictionary. Nuclear norm minimization is adopted to minimize the …

2016-10-14cs.CV

A New Approach To Two-View Motion Segmentation Using Global Dimension Minimization

We present a new approach to rigid-body motion segmentation from two views. We use a previously developed nonlinear embedding of two-view point correspondences into a 9-dimensional space and identify the different motions by segmenting lower-dimensional subspaces. In order to overcome nonuniform distributions along the subspaces, whose dimensions are unknown, we suggest the novel concept of global dimension and its minimization for clustering subspaces with some theoretical motivation. We propose a fast projected gradient algorithm for minimizing global dimension and thus segmenting motions fr…

2014-01-07cs.CV

Practical Matrix Completion and Corruption Recovery using Proximal Alternating Robust Subspace Minimization

National University of Singapore（新加坡国立大学）

Low-rank matrix completion is a problem of immense practical importance. Recent works on the subject often use nuclear norm as a convex surrogate of the rank function. Despite its solid theoretical foundation, the convex version of the problem often fails to work satisfactorily in real-life applications. Real data often suffer from very few observations, with support not meeting the random requirements, ubiquitous presence of noise and potentially gross corruptions, sometimes with these simultaneously occurring. This paper proposes a Proximal Alternating Robust Subspace Minimization (PARSuMi) …

2014-10-28cs.CV

On Unifying Multi-View Self-Representations for Clustering by Tensor Multi-Rank Minimization

Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Technology, Sydney（悉尼科技大学）；The Hong Kong Polytechnic University（香港理工大学）；Xiamen University（厦门大学）

In this paper, we address the multi-view subspace clustering problem. Our method utilizes the circulant algebra for tensor, which is constructed by stacking the subspace representation matrices of different views and then rotating, to capture the low rank tensor subspace so that the refinement of the view-specific subspaces can be achieved, as well as the high order correlations underlying multi-view data can be explored.} By introducing a recently proposed tensor factorization, namely tensor-Singular Value Decomposition (t-SVD) \cite{kilmer13}, we can impose a new type of low-rank tensor cons…

2017-08-13cs.CV

更多相关论文收起更多论文

LogDet Rank Minimization with Application to Subspace Clustering

Southern Illinois University（南伊利诺伊大学）；University of Hawaii at Hilo（夏威夷大学希洛分校）

Low-rank matrix is desired in many machine learning and computer vision problems. Most of the recent studies use the nuclear norm as a convex surrogate of the rank operator. However, all singular values are simply added together by the nuclear norm, and thus the rank may not be well approximated in practical problems. In this paper, we propose to use a log-determinant (LogDet) function as a smooth and closer, though non-convex, approximation to rank for obtaining a low-rank representation in subspace clustering. Augmented Lagrange multipliers strategy is applied to iteratively optimize the Log…

2015-07-03cs.CVcs.LGstat.ML

lp-Recovery of the Most Significant Subspace among Multiple Subspaces with Outliers

University of Minnesota（明尼苏达大学）

We assume data sampled from a mixture of d-dimensional linear subspaces with spherically symmetric distributions within each subspace and an additional outlier component with spherically symmetric distribution within the ambient space (for simplicity we may assume that all distributions are uniform on their corresponding unit spheres). We also assume mixture weights for the different components. We say that one of the underlying subspaces of the model is most significant if its mixture weight is higher than the sum of the mixture weights of all other subspaces. We study the recovery of the mos…

2014-01-13cs.CVmath.FAstat.ML

Robust Subspace Clustering via Tighter Rank Approximation

Southern Illinois University（南伊利诺伊大学）

Matrix rank minimization problem is in general NP-hard. The nuclear norm is used to substitute the rank function in many recent studies. Nevertheless, the nuclear norm approximation adds all singular values together and the approximation error may depend heavily on the magnitudes of singular values. This might restrict its capability in dealing with many practical problems. In this paper, an arctangent function is used as a tighter approximation to the rank function. We use it on the challenging subspace clustering problem. For this nonconvex minimization problem, we develop an effective optim…

2015-10-30cs.AIcs.CVcs.LG

在Grassmannian上进行自适应随机梯度下降用于鲁棒低秩子空间恢复与聚类

Adaptive Stochastic Gradient Descent on the Grassmannian for Robust Low-Rank Subspace Recovery and Clustering

Nanjing University of Information Science and Technology（南京信息工程大学）

本文提出GASG21算法，通过在Grassmann流形上进行自适应随机梯度下降，实现从大矩阵中鲁棒地恢复低秩子空间，并通过K子空间扩展实现对受损数据的聚类。

2015-04-18cs.CVcs.NAmath.NA

T-VSS：面向视觉语言模型对抗鲁棒性的测试时视觉子空间引导

T-VSS: Test-Time Visual Subspace Steering for Adversarial Robustness of Vision-Language Models

School of Electrical Engineering, KAIST（韩国科学技术院电气工程学院）

提出T-VSS方法，通过在视觉特征空间中构建样本特定的低秩子空间并学习共享特征校正，直接适应受攻击特征，提升视觉语言模型的对抗鲁棒性，同时保持清洁准确率和效率。

2026-08-17cs.CV

子空间约束的二次矩阵分解：算法与应用

Subspace-Constrained Quadratic Matrix Factorization: Algorithm and Applications

Beijing Normal University（北京师范大学）；Yantai University（烟台大学）

本文提出子空间约束的二次矩阵分解模型，通过交替最小化联合学习切空间、法子空间及二次形式，实验证明其优于现有方法，有效捕获低维结构。

2024-11-07cs.CVcs.LG

Non-local Meets Global: An Integrated Paradigm for Hyperspectral Denoising

RIKEN AIP（理化学研究所先进智能项目中心）；HKUST（香港科技大学）；Paradigm. Inc.（第四范式有限公司）

Non-local low-rank tensor approximation has been developed as a state-of-the-art method for hyperspectral image (HSI) denoising. Unfortunately, with more spectral bands for HSI, while the running time of these methods significantly increases, their denoising performance benefits little. In this paper, we claim that the HSI underlines a global spectral low-rank subspace, and the spectral subspaces of each full band patch groups should underlie this global low-rank subspace. This motivates us to propose a unified spatial-spectral paradigm for HSI denoising. As the new model is hard to optimize, …

2019-03-27cs.CV

Multi-Level Representation Learning for Deep Subspace Clustering

University of Texas at Arlington（德克萨斯大学阿灵顿分校）

This paper proposes a novel deep subspace clustering approach which uses convolutional autoencoders to transform input images into new representations lying on a union of linear subspaces. The first contribution of our work is to insert multiple fully-connected linear layers between the encoder layers and their corresponding decoder layers to promote learning more favorable representations for subspace clustering. These connection layers facilitate the feature learning procedure by combining low-level and high-level information for generating multiple sets of self-expressive and informative re…

2020-01-19cs.CVcs.LGstat.ML

Hyperspectral Mixed Noise Removal via Subspace Representation and Weighted Low-rank Tensor Regularization

Jilin University（吉林大学）

Recently, the low-rank property of different components extracted from the image has been considered in man hyperspectral image denoising methods. However, these methods usually unfold the 3D tensor to 2D matrix or 1D vector to exploit the prior information, such as nonlocal spatial self-similarity (NSS) and global spectral correlation (GSC), which break the intrinsic structure correlation of hyperspectral image (HSI) and thus lead to poor restoration quality. In addition, most of them suffer from heavy computational burden issues due to the involvement of singular value decomposition operatio…

2021-11-13cs.CVcs.GReess.IV