Unsupervised domain adaptation has received significant attention in recent years. Most of existing works tackle the closed-set scenario, assuming that the source and target domains share the exactly same categories. In practice, nevertheless, a target domain often contains samples of classes unseen in source domain (i.e., unknown class). The extension of domain adaptation from closed-set to such open-set situation is not trivial since the target samples in unknown class are not expected to align with the source. In this paper, we address this problem by augmenting the state-of-the-art domain adaptation technique, Self-Ensembling, with category-agnostic clusters in target domain. Specifically, we present Self-Ensembling with Category-agnostic Clusters (SE-CC) -- a novel architecture that steers domain adaptation with the additional guidance of category-agnostic clusters that are specific to target domain. These clustering information provides domain-specific visual cues, facilitating the generalization of Self-Ensembling for both closed-set and open-set scenarios. Technically, clustering is firstly performed over all the unlabeled target samples to obtain the category-agnostic clusters, which reveal the underlying data space structure peculiar to target domain. A clustering branch is capitalized on to ensure that the learnt representation preserves such underlying structure by matching the estimated assignment distribution over clusters to the inherent cluster distribution for each target sample. Furthermore, SE-CC enhances the learnt representation with mutual information maximization. Extensive experiments are conducted on Office and VisDA datasets for both open-set and closed-set domain adaptation, and superior results are reported when comparing to the state-of-the-art approaches.
Pose for Everything: Towards Category-Agnostic Pose Estimation
The Chinese University of Hong Kong（香港中文大学）；SenseTime Research（商汤科技研究院）；The University of Hong Kong（香港大学）；Shanghai AI Laboratory（上海人工智能实验室）；The University of Sydney（悉尼大学）
Adversarial Reconstruction Feedback for Robust Fine-grained Generalization
College of Computer and Engineering, Shandong University of Science and Technology（山东科技大学计算机与工程学院）；School of Software, Dalian University of Technology（大连理工大学软件学院）
Does it Really Count? Assessing Semantic Grounding in Text-Guided Class-Agnostic Counting
Institute of Information Science and Technologies of the National Research Council (ISTI-CNR)（意大利国家研究理事会信息科学与技术研究所）；University of Pisa - Department of Information Engineering（比萨大学信息工程系）
CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation
State Key Laboratory of Robotics, Shenyang Institute of Automation, Chinese Academy of Sciences（中国科学院沈阳自动化研究所机器人学国家重点实验室）；Institutes for Robotics and Intelligent Manufacturing, Chinese Academy of Sciences（中国科学院机器人与智能制造创新研究院）；University of Chinese Academy of Sciences（中国科学院大学）；University of Arkansas at Little Rock（阿肯色大学小石城分校）
Few-Shot Anomaly Detection via Category-Agnostic Registration Learning
College of Information Communications, National University of Defense Technology（国防科技大学信息通信学院）；Cooperative Medianet Innovation Center, Shanghai Jiao Tong University（上海交通大学协同媒体网络创新中心）；National University of Singapore（新加坡国立大学）；King’s College London（伦敦国王学院）；Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）
Towards Distribution-Agnostic Generalized Category Discovery
Zhejiang University（浙江大学）；The Hong Kong University of Science and Technology（香港科技大学）；Centre for Frontier AI Research, A*STAR（新加坡科技研究局前沿人工智能研究中心）；Angelalign Technology Inc.（时代天使科技有限公司）
CNS-Edit++: Category-Agnostic 3D Editing with Coupled Neural Shape Representation
The Chinese University of Hong Kong（香港中文大学）；Lingnan University（岭南大学）；National University of Singapore（新加坡国立大学）；The Hong Kong University of Science and Technology（香港科技大学）；Autodesk AI Lab（欧特克人工智能实验室）；Simon Fraser University（西蒙弗雷泽大学）
GCR: Geometry-Consistent Routing for Task-Agnostic Continual Anomaly Detection
Tsinghua University Shenzhen International Graduate School（清华大学深圳国际研究生院）；Ratel Soft；Affiliated Fifth Hospital, Wenzhou Medical University（温州医学院附属第五医院）；Chinese Medicine Guangdong Laboratory（广东中医药实验室）
Exploring Masked Autoencoders for Sensor-Agnostic Image Retrieval in Remote Sensing
Faculty of Electrical Engineering and Computer Science, Technische Universität Berlin（柏林工业大学电机工程与计算机科学学院）；BIFOLD - Berlin Institute for the Foundations of Learning and Data（柏林学习与数据基础研究所）；École Polytechnique Fédérale de Lausanne (EPFL)（洛桑联邦理工学院）；Environmental Computational Science and Earth Observation Laboratory (ECEO)（环境计算科学与地球观测实验室）
LarvSeg: Exploring Image Classification Data For Large Vocabulary Semantic Segmentation via Category-wise Attentive Classifier
School of Intelligence Science and Technology, Peking University（北京大学智能科学与技术学院）；Center of Data Science, Peking University（北京大学数据科学中心）；Microsoft Research Asia（微软亚洲研究院）
