Rethinking the Misalignment Problem in Dense Object Detection
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Beijing Institute of Technology(北京理工大学)
Yang Yang, Min Li, Bo Meng, Junxing Ren, Degang Sun, Zihao Huang
Object detection aims to localize and classify the objects in a given image, and these two tasks are sensitive to different object regions. Therefore, some locations predict high-quality bounding boxes but low classification scores, and some locations are quite the opposite. A misalignment exists between the two tasks, and their features are spatially entangled. In order to solve the misalignment problem, we propose a plug-in Spatial-disentangled and Task-aligned operator (SALT). By predicting two task-aware point sets that are located in each task's sensitive regions, SALT can reassign features from those regions and align them to the corresponding anchor point. Therefore, features for the two tasks are spatially aligned and disentangled. To minimize the difference between the two regression stages, we propose a Self-distillation regression (SDR) loss that can transfer knowledge from the refined regression results to the coarse regression results. On the basis of SALT and SDR loss, we propose SALT-Net, which explicitly exploits task-aligned point-set features for accurate detection results. Extensive experiments on the MS-COCO dataset show that our proposed methods can consistently boost different state-of-the-art dense detectors by $\sim$2 AP. Notably, SALT-Net with Res2Net-101-DCN backbone achieves 53.8 AP on the MS-COCO test-dev.
Mask is All You Need: Rethinking Mask R-CNN for Dense and Arbitrary-Shaped Scene Text Detection
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Guangzhou University(广州大学);Mashang Consumer Finance Co., Ltd.(马上消费金融股份有限公司)
VPNeXt -- Rethinking Dense Decoding for Plain Vision Transformer
School of Information and Software Engineering, University of Electronic Science and Technology of China(信息与软件工程学院,电子科学与技术大学);Shenzhen Institute for Advanced Study, University of Electronic Science and Technology of China(深圳先进研究所,电子科学与技术大学)
Point Linguist Model: Segment Any Object via Bridged Large 3D-Language Model
Department of Computer Science, Aberystwyth University(计算机科学系,阿伯里斯特维斯大学);School of Computer Science, University of Sheffield(计算机科学学院,谢菲尔德大学);Department of Automation, Tsinghua University(自动化系,清华大学)
MNet: Rethinking 2D/3D Networks for Anisotropic Medical Image Segmentation
Southeast University(东南大学);Jiangsu Provincial Joint International Research Laboratory of Medical Information Processing(江苏省医学信息处理联合国际研究实验室);Centre de Recherche en Information Biomédicale Sino-Français (CRIBs)(中法生物医学信息研究中心(CRIBs))
厚切片扫描的性质导致3D医学图像的严重切片间不连续性,并且vanilla 2D/3D卷积神经网络(CNN)无法以平衡的方式表示稀疏的切片间信息和密集的切片内信息,导致严重的切片间特征欠拟合(对于vanilla 2D CNN)和过度拟合来自远程切片的噪声(对于vanilla 3D CNN)。在这项工作中,提出了一种新的网状网(MNet),通过学习来平衡轴间的空间表示。1)我们的MNet通过将多维卷积深度嵌入基本模块,潜在地融合了大量的表示过程,使得表示过程的选择灵活,从而自适应地平衡稀疏切片间信息和密集切片内信息的表示。2)我们的MNet潜在地融合了每个基本模块内部的多维特征,同时利用2D(2D视图中易于识别的区域的高分割精度)和3D(3D器官轮廓的高平滑度)表示的优势,从而获得更准确的目标区域建模。在四个公共数据集(CT\&MR)上进行了综合实验,实验结果一致表明所提出的MNet方法优于其他方法.代码和数据集可在以下网址获得:https://github.com/zfdong-code/MNet
Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation
University of Waterloo(滑铁卢大学);Waterloo Artificial Intelligence Institute(滑铁卢人工智能研究所)
在人体姿态估计等关键点估计任务中,基于热图的回归是主要方法,尽管具有显著的缺点:热图本质上存在量化误差,并且需要过多的计算来生成和后处理。为了找到更有效的解决方案,我们提出对各个关键点和空间相关关键点的集合(即,姿势)作为密集单级基于锚的检测框架内的对象。因此,我们将我们的方法称为KAPAO(发音为“Ka-Pow”),用于Keypoints And Poses As Objects。KAPAO适用于单阶段多人人体姿态估计的问题,同时检测人体姿态和关键点对象,并融合检测,以利用两个对象表示的优势。在实验中,我们观察到KAPAO比以前的方法更快,更准确,后者受到热图后处理的严重影响。当不使用测试时间增加时,在实际设置中,精度-速度的折衷是特别有利的。源代码:https://github.com/wmcnally/kapao。
Rethinking the Encoding and Annotating of 3D Bounding Box: Corner-Aware 3D Object Detection from Point Clouds
School of Computer Science, Beijing Institute of Technology(计算机科学学院,北京理工大学);Computer Science Program, Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division, Center of Excellence for Smart Health, and Center of Excellence for Generative AI, King Abdullah University of Science and Technology (KAUST)(计算机科学项目,计算机、电气和数学科学与工程(CEMSE)部门,智能健康卓越中心,生成人工智能卓越中心,国王阿卜杜勒·阿齐兹大学科学与技术(KAUST));State Key Laboratory of Internet of Things for Smart City, Department of Computer and Information Science, University of Macau(智慧城市物联网国家重点实验室,澳门大学计算机与信息科学系);Guangdong Provincial Key Laboratory of Machine Perception and Intelligent Computing, Shenzhen MSU-BIT University(广东省机器感知与智能计算重点实验室,深圳MSU-BIT大学);Beijing Key Laboratory of Intelligent Information Technology, School of Computer Science, Beijing Institute of Technology(北京智能信息技术重点实验室,计算机科学学院,北京理工大学)
The Devil is in the Details: Boosting Guided Depth Super-Resolution via Rethinking Cross-Modal Alignment and Aggregation
Nankai University(南开大学);South China University of Technology(华南理工大学);Peking University(北京大学);Henan Institute of Science and Technology(河南科技学院);MicroBT Electronics Technology Co., Ltd(深圳比特微电子科技有限公司)
Ret3D: Rethinking Object Relations for Efficient 3D Object Detection in Driving Scenes
Nankai University(南开大学);Alibaba DAMO Academy(阿里巴巴达摩院);University of Electronic Science and Technology of China(电子科技大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所);ETH Zurich(苏黎世联邦理工学院)
Rethinking Dense Optical Flow without Test-Time Scaling
Visual and Spatial AI Lab(视觉与空间人工智能实验室);VCCM Section College of PVFA(VCCM学院光电工程学院);Department of ECEN(电子工程系);Department of CSCE(计算机科学与工程系);Texas A&M University(德克萨斯A&M大学)
Rethinking the competition between detection and ReID in Multi-Object Tracking
University of Electronic Science and Technology of China(电子科技大学);Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);University of Chinese Academy of Sciences(中国科学院大学);CAS Center for Excellence in Brain Science and Intelligence Technology(中国科学院脑科学与智能技术卓越创新中心)
Rethinking the Detail-Preserved Completion of Complex Tubular Structures based on Point Cloud: a Dataset and a Benchmark
Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications (Southeast University), Ministry of Education(新一代人工智能技术及其交叉应用重点实验室(东南大学));Jiangsu Province Joint International Research Laboratory of Medical Information Processing(江苏省医学信息处理联合国际研究实验室);The First Affiliated Hospital of Nanjing Medical University(南京医科大学第一附属医院)