Universal Domain Adaptation (UniDA) targets knowledge transfer in the presence of both covariate and label shifts. Recently, Source-free Universal Domain Adaptation (SF-UniDA) has emerged to achieve UniDA without access to source data, which tends to be more practical due to data protection policies. The main challenge lies in determining whether covariate-shifted samples belong to target-private unknown categories. Existing methods tackle this either through hand-crafted thresholding or by developing time-consuming iterative clustering strategies. In this paper, we propose a new idea of LEArning Decomposition (LEAD), which decouples features into source-known and -unknown components to identify target-private data. Technically, LEAD initially leverages the orthogonal decomposition analysis for feature decomposition. Then, LEAD builds instance-level decision boundaries to adaptively identify target-private data. Extensive experiments across various UniDA scenarios have demonstrated the effectiveness and superiority of LEAD. Notably, in the OPDA scenario on VisDA dataset, LEAD outperforms GLC by 3.5% overall H-score and reduces 75% time to derive pseudo-labeling decision boundaries. Besides, LEAD is also appealing in that it is complementary to most existing methods. The code is available at https://github.com/ispc-lab/LEAD.
Joint Distribution Alignment for Universal Domain Adaptation
School of Software Engineering, South China University of Technology（华南理工大学软件工程学院）；School of Future Technology, South China University of Technology（华南理工大学未来技术学院）；College of Computer Science, Chongqing University（重庆大学计算机学院）
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models for Task-Aware Parameter-Efficient Fine-tuning
King Abdullah University of Science and Technology (KAUST)（阿卜杜拉国王科技大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；University of Sydney（悉尼大学）
South China University of Technology（华南理工大学）；Hong Kong Polytechnic University（香港理工大学）
在本文中，我们研究了一个可以说是最少的限制设置的领域自适应在实际部署的意义上，只有源模型的接口是可用的目标域，并允许两个域之间的标签空间关系是不同的和未知的。我们将这样的设置称为通用黑盒领域自适应（UB $^2$ DA）。然而，由于领域自适应只能通过访问源模型的接口，依赖于部分重叠标签空间中未标记目标数据的预测，因此UB $^2$ DA带来了巨大的学习挑战。为了应对这些挑战，我们首先注意到学习任务可以转换为类内\footnote{In this paper we use in-class (out-class) to describe the classes observed (not observed) in the source black-box model.}判别和类外检测两个子任务，它们可以分别通过模型蒸馏和熵分离来学习。我们建议将它们统一到一个自训练框架中，通过目标样本局部邻域中预测的一致性进行正则化。我们的框架是简单的，强大的，易于优化。在领域自适应基准上的实验表明了该方法的有效性。值得注意的是，通过仅访问源模型的接口，我们的框架优于现有的通用领域自适应方法，这些方法利用源数据和/或源模型，具有新提出的（并且可以说是更合理的）H分数度量，并且与平均类准确度度量的性能相当。
AdaptGuard: Defending Against Universal Attacks for Model Adaptation
University of Science and Technology of China（中国科学技术大学）；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）；Nanjing University（南京大学）
Dynamic Context-oriented Decomposition for Task-aware Low-rank Adaptation with Less Forgetting and Faster Convergence
King Abdullah University of Science and Technology, Saudi Arabia（卡布尔大学）；University of California, Merced, USA（加州大学梅尔德分校）；University of Oxford, U.K.（牛津大学）
Decomposition-Based Domain Adaptation for Real-World Font Recognition
我们提出了一个域自适应框架，以解决合成训练和真实世界的测试数据之间的域不匹配。我们展示了我们的方法上一个具有挑战性的细粒度分类问题：识别字体风格的文本图像。在这个任务中，生成大量的渲染字体示例非常容易，但很难获得真实世界的标记图像。在以前的字体识别方法中，这种真实到合成域的差距导致了对新真实数据的泛化能力差（Chen et al.（2014））。在本文中，我们介绍了一种卷积神经网络分解方法，利用一个大型的训练语料库的合成数据，以获得有效的特征进行分类。这是使用基于堆叠卷积自动编码器的自适应技术来完成的，堆叠卷积自动编码器利用大量未标记的真实世界文本图像与以特定方式预处理的合成数据相结合。所提出的DeepFont方法在我们收集的一个新的大型标记真实世界数据集上实现了高于80%（前5名）的准确率。
Universal Semi-Supervised Domain Adaptation by Mitigating Common-Class Bias
National University of Singapore (NUS)（新加坡国立大学）；Centre for Frontier AI Research (CFAR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局前沿人工智能研究中心）；Institute for Infocomm Research (IR), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局信息通信研究所）
Decomposition-based Unsupervised Domain Adaptation for Remote Sensing Image Semantic Segmentation
School of Science and Engineering, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）理工学院）；School of Information Science and Engineering, Wuhan University of Science and Technology（武汉科技大学信息科学与工程学院）；School of Cyber Science and Engineering, Wuhan University（武汉大学网络空间安全学院）；School of Electronic Engineering and Computer Science, Peking University（北京大学电子工程与计算机科学学院）
LoCA: Location-Aware Cosine Adaptation for Parameter-Efficient Fine-Tuning
University of Electronic Science and Technology of China（电子科技大学）；The University of Melbourne（墨尔本大学）；Nankai University（南开大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
Target Semantics Clustering via Text Representations for Robust Universal Domain Adaptation
University of Science and Technology of China（中国科学技术大学）；Institute of Artificial Intelligence, Hefei Comprehensive National Science Center（合肥综合性国家科学中心人工智能研究院）
Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）
USBD: Universal Structural Basis Distillation for Source-Free Graph Domain Adaptation
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Zhengzhou University（郑州大学）；The Hebei University of Technology（河北工业大学）；The City University of Hong Kong（香港城市大学）
COCA: Classifier-Oriented Calibration via Textual Prototype for Source-Free Universal Domain Adaptation
School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；Institute of High Performance Computing (IHPC), Agency for Science, Technology and Research (A*STAR)（新加坡科技研究局高性能计算研究所）；University of Chinese Academy of Sciences（中国科学院大学）
