In this paper, we address the problem of weakly supervised object localization (WSL), which trains a detection network on the dataset with only image-level annotations. The proposed approach is built on the observation that the proposal set from the training dataset is a collection of background, object parts, and objects. Several strategies are taken to adaptively eliminate the noisy proposals and generate pseudo object-level annotations for the weakly labeled dataset. A multiple instance learning (MIL) algorithm enhanced by mask-out strategy is adopted to collect the class-specific object proposals, which are then utilized to adapt a pre-trained classification network to a detection network. In addition, the detection results from the detection network are re-weighted by jointly considering the detection scores and the overlap ratio of proposals in a proposal subset optimization framework. The optimal proposals work as object-level labels that enable a pseudo-strongly supervised dataset for training the detection network. Consequently, we establish a fully adaptive detection network. Extensive evaluations on the PASCAL VOC 2007 and 2012 datasets demonstrate a significant improvement compared with the state-of-the-art methods.
Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver
North Carolina State University（北卡罗来纳州立大学）；University of Central Florida（中佛罗里达大学）；Wuhan University（武汉大学）；OPPO Seattle Research Center（OPPO西雅图研究中心）；Westlake University（西湖大学）
High-Quality Proposal Encoding and Cascade Denoising for Imaginary Supervised Object Detection
Institute of Cyberspace Security, Harbin Institute of Technology, Shenzhen（网络安全研究所，哈尔滨工业大学，深圳）；Department of New Networks, Peng Cheng Laboratory（新网络部门，鹏城实验室）；School of Cyberspace Science, Harbin Institute of Technology（空间科学学院，哈尔滨工业大学）；Center on Machine Learning Research, Harbin Institute of Technology（机器学习研究中心，哈尔滨工业大学）；Faculty of Information Technology, Monash University（信息技术学院，墨尔本大学）
C-DiffDet+: Fusing Global Scene Context with Generative Denoising for High-Fidelity Car Damage Detection
organization= Department of Innovation Engineering, University of Salento \& Institute of Applied Sciences；organization= Electrical Engineering Department , addressline= Mohamed Khider University of Biskra , postcode= 07000 , city= Biskra , country= Algeria；organization= UPV/EHU , addressline= University of the Basque Country , city= Sebastian , postcode= 20018 , state= Sebastian , country= Spain；organization= Sorbonne University Abu Dhabi , addressline= Al Reem Island, P.O. Box 34105 , city= Abu Dhabi , postcode= 34105 , state= Abu Dhabi , country= United Arab Emirates；organization= CNR-STIIMA, Institute of Intelligent Industrial Systems；Technologies for Advanced Manufacturing , addressline= c/o Campus Ecotekne, Via Monteroni , city= Lecce , postcode= 73100 , state= LE , country= Italy；organization= Institute of Applied Sciences
DiffTAD: Temporal Action Detection with Proposal Denoising Diffusion
University of Surrey（萨里大学）；iFlyTek-Surrey Joint Research Center on Artificial Intelligence（科大讯飞-萨里人工智能联合研究中心）；Surrey Institute for People-Centred Artificial Intelligence（萨里以人为本人工智能研究所）；Imperial College London（伦敦帝国理工学院）
Iterative Low-rank Network for Hyperspectral Image Denoising
School of Computer Science and Engineering, Nanjing University of Science and Technology（计算机科学与工程学院，南京理工大学）；School of Information and Communication Technology, Griffith University（信息与通信技术学院，格里菲斯大学）；College of Computer Science, Zhejiang University（计算机科学学院，浙江大学）
One-Shot Object Detection with Co-Attention and Co-Excitation
National Tsing Hua University（国立清华大学）；Aeolus Robotics（风神机器人公司）；Academia Sinica（中央研究院）；Taiwan AI Labs（台湾人工智能实验室）
本文旨在解决一次性目标检测这一具有挑战性的问题。给定查询图像块，其类别标签不包括在训练数据中，任务的目标是检测目标图像中相同类别的所有实例。为此，我们开发了一种新的{ \em co-attention and co-excitation}（CoAE）框架，在三个关键技术方面做出了贡献。首先，我们建议使用非本地操作来探索每个查询目标对中体现的共同注意力，并考虑一次性情况下的产量区域建议。其次，我们制定了一个挤压和共激发方案，可以自适应地强调相关的功能通道，以帮助发现相关的建议，并最终的目标对象。第三，我们设计了一个基于边缘的排名损失，用于隐式学习一个度量来预测区域建议与底层查询的相似性，无论其类标签在训练中是否可见。因此，所得到的模型是一个两阶段的检测器，在检测可见和从未见过的类别的对象的一次性设置下，在VOC和MS-COCO上产生强基线。代码可在https://github.com/timy90022/One-Shot-Object-Detection上获得。
Dense Hybrid Proposal Modulation for Lane Detection
Beijing University of Posts and Telecommunications（北京邮电大学）；Tsinghua University（清华大学）；Beijing National Research Center for Information Science and Technology（北京信息科学与技术国家研究中心）
A TRPCA-Inspired Deep Unfolding Network for Hyperspectral Image Denoising via Thresholded t-SVD and Top-K Sparse Transformer
College of Computer Science and Engineering, Shandong University of Science and Technology（计算机科学与工程学院，山东科技大学）；Gosci Information Technology Co.,Ltd.（Gosci信息技术有限公司）
UniPET: a universal network for high-quality PET image denoising across varied dose reduction factors
School of Biological Science and Medical Engineering（生物科学与医学工程学院）；State Key Laboratory of Software Development Environment（软件开发环境国家重点实验室）；Key Laboratory of Biomechanics, Mechanobiology of Ministry of Education（教育部生物力学与机械生物学重点实验室）；Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University（北京生物医学工程先进创新中心，北航）；Department of Biomedical Engineering（生物医学工程系）；Department of Gynecology Oncology（妇科肿瘤科）；National Cancer Center/National Clinical Research Center for Cancer/Cancer Hospital（国家癌症中心/国家癌症临床研究中心/癌症医院）；Chinese Academy of Medical Sciences（中国医学科学院）；Peking Union Medical College（北京协和医学院）；Xiaomi Corporation（小米公司）
Test-time Adaptive Hierarchical Co-enhanced Denoising Network for Reliable Multimodal Classification
The Guangdong Provincial Key Laboratory of Computational Intelligence and Cyberspace Information, the School of Computer Science and Engineering, South China University of Technology（广东省计算智能与网络信息重点实验室、计算机科学与工程学院、华南理工大学）；The Pazhou Laboratory（琶洲实验室）
