Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation

• URL: http://arxiv.org/abs/2509.11264v1
• Date: Sun, 14 Sep 2025 13:27:46 GMT
• Title: Cross-Domain Attribute Alignment with CLIP: A Rehearsal-Free Approach for Class-Incremental Unsupervised Domain Adaptation
• Authors: Kerun Mi, Guoliang Kang, Guangyu Li, Lin Zhao, Tao Zhou, Chen Gong,
• Abstract summary: Class-Incremental Unsupervised Domain Adaptation (CI-UDA) aims to adapt a model from a labeled source domain to an unlabeled target domain.<n>The key to solving this problem lies in avoiding catastrophic forgetting of knowledge about previous target classes.<n>We propose to mine and preserve domain-invariant and class-agnostic knowledge to facilitate the CI-UDA task.
• Score: 27.40776917141145
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Class-Incremental Unsupervised Domain Adaptation (CI-UDA) aims to adapt a model from a labeled source domain to an unlabeled target domain, where the sets of potential target classes appearing at different time steps are disjoint and are subsets of the source classes. The key to solving this problem lies in avoiding catastrophic forgetting of knowledge about previous target classes during continuously mitigating the domain shift. Most previous works cumbersomely combine two technical components. On one hand, they need to store and utilize rehearsal target sample from previous time steps to avoid catastrophic forgetting; on the other hand, they perform alignment only between classes shared across domains at each time step. Consequently, the memory will continuously increase and the asymmetric alignment may inevitably result in knowledge forgetting. In this paper, we propose to mine and preserve domain-invariant and class-agnostic knowledge to facilitate the CI-UDA task. Specifically, via using CLIP, we extract the class-agnostic properties which we name as "attribute". In our framework, we learn a "key-value" pair to represent an attribute, where the key corresponds to the visual prototype and the value is the textual prompt. We maintain two attribute dictionaries, each corresponding to a different domain. Then we perform attribute alignment across domains to mitigate the domain shift, via encouraging visual attention consistency and prediction consistency. Through attribute modeling and cross-domain alignment, we effectively reduce catastrophic knowledge forgetting while mitigating the domain shift, in a rehearsal-free way. Experiments on three CI-UDA benchmarks demonstrate that our method outperforms previous state-of-the-art methods and effectively alleviates catastrophic forgetting. Code is available at https://github.com/RyunMi/VisTA.

Related papers

• Prototypical Contrast Adaptation for Domain Adaptive Semantic Segmentation [52.63046674453461]
  Prototypical Contrast Adaptation (ProCA) is a contrastive learning method for unsupervised domain adaptive semantic segmentation. ProCA incorporates inter-class information into class-wise prototypes, and adopts the class-centered distribution alignment for adaptation.
  arXiv  Detail & Related papers  (2022-07-14T04:54:26Z)
• Multi-Level Features Contrastive Networks for Unsupervised Domain Adaptation [6.934905764152813]
  Unsupervised domain adaptation aims to train a model from the labeled source domain to make predictions on the unlabeled target domain. Existing methods tend to align the two domains directly at the domain-level, or perform class-level domain alignment based on deep feature. In this paper, we develop this work on the method of class-level alignment.
  arXiv  Detail & Related papers  (2021-09-14T09:23:27Z)
• Cross-domain Contrastive Learning for Unsupervised Domain Adaptation [108.63914324182984]
  Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a fully-labeled source domain to a different unlabeled target domain. We build upon contrastive self-supervised learning to align features so as to reduce the domain discrepancy between training and testing sets.
  arXiv  Detail & Related papers  (2021-06-10T06:32:30Z)
• Contrastive Learning and Self-Training for Unsupervised Domain Adaptation in Semantic Segmentation [71.77083272602525]
  UDA attempts to provide efficient knowledge transfer from a labeled source domain to an unlabeled target domain. We propose a contrastive learning approach that adapts category-wise centroids across domains. We extend our method with self-training, where we use a memory-efficient temporal ensemble to generate consistent and reliable pseudo-labels.
  arXiv  Detail & Related papers  (2021-05-05T11:55:53Z)
• Prototypical Cross-domain Self-supervised Learning for Few-shot Unsupervised Domain Adaptation [91.58443042554903]
  We propose an end-to-end Prototypical Cross-domain Self-Supervised Learning (PCS) framework for Few-shot Unsupervised Domain Adaptation (FUDA) PCS not only performs cross-domain low-level feature alignment, but it also encodes and aligns semantic structures in the shared embedding space across domains. Compared with state-of-the-art methods, PCS improves the mean classification accuracy over different domain pairs on FUDA by 10.5%, 3.5%, 9.0%, and 13.2% on Office, Office-Home, VisDA-2017, and DomainNet, respectively.
  arXiv  Detail & Related papers  (2021-03-31T02:07:42Z)
• Surprisingly Simple Semi-Supervised Domain Adaptation with Pretraining and Consistency [93.89773386634717]
  Visual domain adaptation involves learning to classify images from a target visual domain using labels available in a different source domain. We show that in the presence of a few target labels, simple techniques like self-supervision (via rotation prediction) and consistency regularization can be effective without any adversarial alignment to learn a good target classifier. Our Pretraining and Consistency (PAC) approach, can achieve state of the art accuracy on this semi-supervised domain adaptation task, surpassing multiple adversarial domain alignment methods, across multiple datasets.
  arXiv  Detail & Related papers  (2021-01-29T18:40:17Z)
• Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentation [95.10255219396109]
  We propose a fine-grained adversarial learning strategy for class-level feature alignment. We adopt a fine-grained domain discriminator that not only plays as a domain distinguisher, but also differentiates domains at class level. An analysis with Class Center Distance (CCD) validates that our fine-grained adversarial strategy achieves better class-level alignment.
  arXiv  Detail & Related papers  (2020-07-17T20:50:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.