Unsupervised Layered Image Decomposition into Object Prototypes
LIGM, École des Ponts, Univ Gustave Eiffel, CNRS（LIGM，巴黎高科路桥学校，古斯塔夫·埃菲尔大学，法国国家科学研究中心）；Inria and DIENS (ENS-PSL, CNRS, Inria)（法国国家信息与自动化研究所和DIENS（巴黎高等师范学院-巴黎文理研究大学，法国国家科学研究中心，法国国家信息与自动化研究所））；Center for Data Science, New York University（纽约大学数据科学中心）
Tom Monnier, Elliot Vincent, Jean Ponce, Mathieu Aubry
We present an unsupervised learning framework for decomposing images into layers of automatically discovered object models. Contrary to recent approaches that model image layers with autoencoder networks, we represent them as explicit transformations of a small set of prototypical images. Our model has three main components: (i) a set of object prototypes in the form of learnable images with a transparency channel, which we refer to as sprites; (ii) differentiable parametric functions predicting occlusions and transformation parameters necessary to instantiate the sprites in a given image; (iii) a layered image formation model with occlusion for compositing these instances into complete images including background. By jointly learning the sprites and occlusion/transformation predictors to reconstruct images, our approach not only yields accurate layered image decompositions, but also identifies object categories and instance parameters. We first validate our approach by providing results on par with the state of the art on standard multi-object synthetic benchmarks (Tetrominoes, Multi-dSprites, CLEVR6). We then demonstrate the applicability of our model to real images in tasks that include clustering (SVHN, GTSRB), cosegmentation (Weizmann Horse) and object discovery from unfiltered social network images. To the best of our knowledge, our approach is the first layered image decomposition algorithm that learns an explicit and shared concept of object type, and is robust enough to be applied to real images.
Explaining Radiological Emphysema Subtypes with Unsupervised Texture Prototypes: MESA COPD Study
Columbia University（哥伦比亚大学）；Columbia University Medical Center（哥伦比亚大学医学中心）；McGill University Health Center（麦吉尔大学健康中心）；University of Iowa（爱荷华大学）；National Institutes of Health（美国国立卫生研究院）
Distribution Aligned Diffusion and Prototype-guided network for Unsupervised Domain Adaptive Segmentation
Xi’an Jiaotong University（西安交通大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；University of California, Santa Cruz（加州大学圣克鲁兹分校）
Prototype-Guided Continual Adaptation for Class-Incremental Unsupervised Domain Adaptation
Peking University（北京大学）；South China University of Technology（华南理工大学）；National University of Singapore（新加坡国立大学）；MIT-IBM Watson AI Lab（麻省理工学院-IBM沃森人工智能实验室）
CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
The University of Hong Kong（香港大学）；Cruise；Yale University（耶鲁大学）；Shanghai AI Laboratory（上海人工智能实验室）；HKU Shanghai Intelligent Computing Research Center（香港大学上海智能计算研究中心）
Multi-Granularity Class Prototype Topology Distillation for Class-Incremental Source-Free Unsupervised Domain Adaptation
Hangzhou Dianzi University（杭州电子科技大学）；Macao Polytechnic University（澳门理工大学）；Beijing Institute of Technology（北京理工大学）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Unified Unsupervised and Sparsely-Supervised 3D Object Detection by Semantic Pseudo-Labeling and Prototype Learning
Institute of Medical Robotics, Shanghai Jiao Tong University（上海交通大学医疗机器人研究院）；Key Laboratory of System Control and Information Processing, Ministry of Education of China（系统控制与信息处理教育部重点实验室）
Attentive Prototypes for Source-free Unsupervised Domain Adaptive 3D Object Detection
Johns Hopkins University（约翰斯·霍普金斯大学）
3D目标检测网络往往偏向于它们所训练的数据。对与训练（源）数据不同的位置、条件或传感器捕获的数据集进行评估，由于与测试（或目标）数据的分布差距，导致模型性能下降。用于领域自适应的当前方法或者假设在训练期间访问源数据，这可能由于隐私或存储器问题而不可用，或者需要激光雷达帧序列作为输入。我们提出了一种用于基于激光雷达的3D对象检测器的无源、无监督领域自适应的单帧方法，该方法使用类原型来减轻伪标签噪声的影响。为了解决传统特征聚合方法在存在噪声标签的情况下用于原型计算的局限性，我们利用Transformer模块来识别与不正确、过度自信的注释相对应的离群ROI，并计算出一个专注的类原型。在迭代训练策略下，与噪声伪标签相关联的损失被降权，从而在自训练过程中被细化。为了验证我们提出的方法的有效性，我们检查了与在大型标签丰富的数据集（如Waymo Open Dataset和nuScenes）上训练的网络相关的域转移，并在较小的标签贫乏的数据集（如KITTI）上进行评估，反之亦然。我们证明了我们的方法在两个最近的对象检测器，并取得优于其他领域自适应作品的结果。
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
Institute of Artificial Intelligence, Xiamen University（厦门大学人工智能研究院）；Shanghai Innovation Institute（上海创新研究院）；School of Informatics, Xiamen University（厦门大学信息学院）；East China Normal University（华东师范大学）
Temporal Prototyping and Hierarchical Alignment for Unsupervised Video-based Visible-Infrared Person Re-Identification
College of Control Science and Engineering, Zhejiang University（控制科学与工程学院，浙江大学）；School of Computer Science and Technology, Zhejiang University of Water Resources and Electric Power（计算机科学与技术学院，浙江水利电力大学）
ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation
Peking University（北京大学）；Peking University Shenzhen Graduate School（北京大学深圳研究生院）；Peng Cheng Laboratory（鹏城实验室）；Dalian University of Technology（大连理工大学）；Tsinghua University（清华大学）
Pixel-wise Agricultural Image Time Series Classification: Comparisons and a Deformable Prototype-based Approach
LIGM, Ecole des Ponts, Univ Gustave Eiffel, CNRS（LIGM实验室、巴黎路桥学校、古斯塔夫·埃菲尔大学、法国国家科学研究中心）；Inria Paris（巴黎信息与自动化研究所）；Ecole normale superieure (ENS-PSL, CNRS, Inria)（巴黎高等师范学院（PSL大学成员）、法国国家科学研究中心、法国信息与自动化研究所）；Center for Data Science, New York University（纽约大学数据科学中心）
Beyond Single Images: Retrieval Self-Augmented Unsupervised Camouflaged Object Detection
College of Artificial Intelligence, Nankai University, China（南开大学人工智能学院）；Department of Computing, The Hong Kong Polytechnic University, Hong Kong（香港理工大学计算机系）；School of Computer and Information, Anhui Normal University, China（安徽师范大学计算机与信息学院）
