Domain Adaptation (DA) attempts to transfer knowledge learned in the labeled source domain to the unlabeled but related target domain without requiring large amounts of target supervision. Recent advances in DA mainly proceed by aligning the source and target distributions. Despite the significant success, the adaptation performance still degrades accordingly when the source and target domains encounter a large distribution discrepancy. We consider this limitation may attribute to the insufficient exploration of domain-specialized features because most studies merely concentrate on domain-general feature learning in task-specific layers and integrate totally-shared convolutional networks (convnets) to generate common features for both domains. In this paper, we relax the completely-shared convnets assumption adopted by previous DA methods and propose Domain Conditioned Adaptation Network (DCAN), which introduces domain conditioned channel attention module with a multi-path structure to separately excite channel activation for each domain. Such a partially-shared convnets module allows domain-specialized features in low-level to be explored appropriately. Further, given the knowledge transferability varying along with convolutional layers, we develop Generalized Domain Conditioned Adaptation Network (GDCAN) to automatically determine whether domain channel activations should be separately modeled in each attention module. Afterward, the critical domain-specialized knowledge could be adaptively extracted according to the domain statistic gaps. As far as we know, this is the first work to explore the domain-wise convolutional channel activations separately for deep DA networks. Additionally, to effectively match high-level feature distributions across domains, we consider deploying feature adaptation blocks after task-specific layers, which can explicitly mitigate the domain discrepancy.
Beijing Institute of Technology（北京理工大学）；Indiana University-Purdue University Indianapolis（印第安纳大学与普渡大学印第安纳波利斯联合分校）；Tsinghua University（清华大学）；Didi Chuxing（滴滴出行）；Syracuse University（雪城大学）
Computer Vision Center, Universitat Autonoma de Barcelona（计算机视觉中心，巴塞罗那自治大学）；PCALab, Nanjing University of Science and Technology（南京理工大学PCALab）；Huawei Kirin Solution（华为麒麟解决方案）
Self-Rule to Multi-Adapt: Generalized Multi-source Feature Learning Using Unsupervised Domain Adaptation for Colorectal Cancer Tissue Detection
EPFL（洛桑联邦理工学院）；University of Fribourg（弗里堡大学）；University of Bern（伯尔尼大学）
监督学习受到标记数据可用性的限制，在数字病理学领域获取标记数据尤其昂贵。利用源数据进行预训练或使用领域自适应可以是克服这个问题的一种方法。然而，预先训练的网络往往无法推广到新的测试域，这些测试域由于组织染色，类型和纹理变化而分布不相同。此外，当前的领域自适应方法主要依赖于完全标记的源数据集。在这项工作中，我们提出了自规则多适应（SRMA），它利用自监督学习来执行领域自适应，并消除了完全标记的源数据集的必要性。SRMA可以有效地将从几个标记的源域的数据获得的判别知识转移到一个新的目标域，而不需要额外的组织注释。我们的方法利用这两个领域的结构，通过捕捉视觉相似性与域内和跨域的自我监督。此外，我们提出了一个广义的制定我们的方法，允许框架从多个源域学习。我们表明，我们提出的方法优于基线的结直肠组织类型分类\new{in single and multi-source settings}的领域自适应，并进一步验证我们的方法在内部临床队列。代码和训练的模型可以在https://github.com/christianabbet/SRA上开源。
Category Adaptation Meets Projected Distillation in Generalized Continual Category Discovery
IDEAS NCBR；Warsaw University of Technology（华沙理工大学）；Gdańsk University of Technology（格但斯克理工大学）；Tooploox；Autonomous University of Barcelona（巴塞罗那自治大学）；Computer Vision Center（计算机视觉中心）
SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
College of Computer Science（计算机科学学院）；Technology, Zhejiang University（技术学院，浙江大学）；School of Software Technology（软件技术学校）；Electronic Engineering, Hunan University（电子工程，湖南大学）
Online Adaptation of Visual Odometry Frontends with Image-Conditioned Reinforcement Learning
Robotics and Perception Group, University of Zurich, Switzerland（苏黎世大学机器人与感知组，瑞士）；Jet Propulsion Laboratory, California Institute of Technology, USA（加州理工学院喷气推进实验室，美国）
Reference-Efficient Multimodal Bitstream-Corrupted Video Recovery via Depth-Conditioned Adaptation
Nanyang Technological University（南洋理工大学）；Huazhong University of Science and Technology（华中科技大学）；Harbin Engineering University（哈尔滨工程大学）；Institute for Infocomm Research, Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局信息通信研究院）；National Tsing Hua University（国立清华大学）
IP-SAM: Rethinking Prompt-Conditioned Segmentation for Prompt-Absent Deployment
University of Chinese Academy of Sciences（中国科学院大学）；Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences（中国科学院空间应用工程与技术中心）
Synergistic Dual-Branch Adaptation for Multi-modal Generalized Category Discovery
College of Computer Science, Nankai University（南开大学计算机学院）；State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所多模态人工智能系统国家重点实验室）
TTA-Vid: Generalized Test-Time Adaptation for Video Reasoning
University of Tübingen（蒂宾根大学）；MIT（麻省理工学院）；IBM Research（IBM研究院）；MIT-IBM Watson AI Lab（MIT-IBM沃森人工智能实验室）；Tuebingen AI Center（蒂宾根人工智能中心）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）
Evidence-Based Text-Conditioned 3D CT Synthesis for Ovarian Cancer
AIRLab, Politecnico di Milano（米兰理工学院AIR实验室）；Politecnico di Milano（米兰理工学院）；NEARLab, Politecnico di Milano（米兰理工学院NEAR实验室）；Istituto Europeo di Oncologia（欧洲肿瘤研究所）；Università degli Studi dell’Insubria（意大利北部大学）；Karlsruhe Institute of Technology（卡尔斯鲁厄理工学院）
Prompt-Conditioned FiLM and Multi-Scale Fusion on MedSigLIP for Low-Dose CT Quality Assessment
Electronics and Communication Engineering Department, Istanbul Technical University, Istanbul, Turkey（伊斯坦布尔技术大学电子与通信工程系）；Electrical and Electronics Engineering Department, Istanbul University, Istanbul, Turkey（伊斯坦布尔大学电气与电子工程系）
