Whereas CNNs have demonstrated immense progress in many vision problems, they suffer from a dependence on monumental amounts of labeled training data. On the other hand, dictionary learning does not scale to the size of problems that CNNs can handle, despite being very effective at low-level vision tasks such as denoising and inpainting. Recently, interest has grown in adapting dictionary learning methods for supervised tasks such as classification and inverse problems. We propose two new network layers that are based on dictionary learning: a sparse factorization layer and a convolutional sparse factorization layer, analogous to fully-connected and convolutional layers, respectively. Using our derivations, these layers can be dropped in to existing CNNs, trained together in an end-to-end fashion with back-propagation, and leverage semisupervision in ways classical CNNs cannot. We experimentally compare networks with these two new layers against a baseline CNN. Our results demonstrate that networks with either of the sparse factorization layers are able to outperform classical CNNs when supervised data are few. They also show performance improvements in certain tasks when compared to the CNN with no sparse factorization layers with the same exact number of parameters.
Human Action Localization with Sparse Spatial Supervision
Xerox Research Centre Europe（施乐欧洲研究中心）；Inria（法国国家信息与自动化研究所）
我们介绍了一种方法，用于时空人体动作定位使用稀疏空间监督。我们的方法利用了当今可用的大量带注释的人类，并通过将最先进的人体检测器与检测跟踪方法相结合来提取人体管道。考虑到这些高质量的人体管和时间监督，我们选择具有非常稀疏的空间监督的阳性管和阴性管，即，每个实例仅一个空间注释帧。选定的管使我们能够有效地学习基于密集轨迹或CNN的时空动作检测器。我们在现有的动作本地化基准：UCF-Sports，J-HMDB和UCF-101上进行实验。我们的结果表明，尽管使用稀疏空间监督，我们的方法与使用完全监督的方法表现相当，即，每帧一个限界框注释。为了进一步验证我们的方法，我们引入了DALY（Daily Action Localization in YouTube），这是一个在空间和时间上进行真实动作定位的数据集。它包含31小时视频（330万帧）中10个动作的3.6k实例的高质量时间和空间注释。它比现有的数据集大一个数量级，具有更多样的外观和较长的未修剪视频。
Compositional Factorization of Visual Scenes with Convolutional Sparse Coding and Resonator Networks
Redwood Center for Theoretical Neuroscience, UC Berkeley（加州大学伯克利分校红木理论神经科学中心）；Université Paris-Saclay（巴黎-萨克雷大学）；Örebro University（厄勒布鲁大学）；Research Institutes of Sweden（瑞典研究院）
Beyond Low-Rank: Low-Rank Sparse Prompting via Spiking Neural Network and Prompt Factorization
Information Materials and Intelligent Sensing Laboratory of Anhui Province（安徽省信息材料与智能感知实验室）；Anhui Provincial Key Laboratory of Multimodal Cognitive Computation（安徽省多模态认知计算重点实验室）；School of Computer Science and Technology, Anhui University（安徽大学计算机科学与技术学院）
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
IBM Research Zurich, Zurich, Switzerland（IBM苏黎世研究实验室，瑞士苏黎世）；ETH Zurich, Computer Vision（苏黎世联邦理工学院，计算机视觉）；ETH AI Center, Switzerland（苏黎世联邦理工学院人工智能中心，瑞士）；ETH Zurich, Photogrammetry（苏黎世联邦理工学院，摄影测量学）；Microsoft, Switzerland（微软公司，瑞士）
Hyperspectral Anomaly Detection via Group Sparse Low-Rank Tensor Factorization With Automatic Anomaly Grouping
Central China Normal University（华中师范大学）；Academy of Mathematics and Systems Science, Chinese Academy of Sciences（中国科学院数学与系统科学研究院）；University of Chinese Academy of Sciences（中国科学院大学）
IceCloudNet: Cirrus and mixed-phase cloud prediction from SEVIRI input learned from sparse supervision
ETH Zurich（苏黎世联邦理工学院）；European Space Agency (ESA)（欧洲空间局）；Consiglio Nazionale delle Ricerche - Istituto di Scienze Marine (CNR-ISMAR)（意大利国家研究委员会-海洋科学研究所）
A Deep Joint Sparse Non-negative Matrix Factorization Framework for Identifying the Common and Subject-specific Functional Units of Tongue Motion During Speech
Massachusetts General Hospital（麻省总医院）；Harvard Medical School（哈佛医学院）；Johns Hopkins University（约翰斯·霍普金斯大学）；University of Maryland School of Dentistry（马里兰大学牙医学院）；Johns Hopkins University School of Medicine（约翰斯·霍普金斯大学医学院）
Salient Sparse Visual Odometry With Pose-Only Supervision
School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；State University of New York at Buffalo（纽约州立大学布法罗分校）
