TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918043976728576 |
|---|---|
| author | Lee, Sohyun Kim, Nayeong Kang, Juwon Oh, Seong Joon Kwak, Suha |
| author_facet | Lee, Sohyun Kim, Nayeong Kang, Juwon Oh, Seong Joon Kwak, Suha |
| contents | This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge. Existing CTTA methods mostly focus on adaptation to the current test domain only, overlooking generalization to arbitrary test domains a model may face in the future. To tackle this limitation, we present a novel online test-time domain generalization framework for CTTA, dubbed TestDG. TestDG aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potential for effective generalization to future domains. To this end, we propose a new model architecture and a test-time adaptation strategy dedicated to learning domain-invariant features, along with a new data structure and optimization algorithm for effectively managing information from previous test domains. TestDG achieved state of the art on four public CTTA benchmarks. Moreover, it showed superior generalization to unseen test domains. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_04981 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | TestDG: Test-time Domain Generalization for Continual Test-time Adaptation Lee, Sohyun Kim, Nayeong Kang, Juwon Oh, Seong Joon Kwak, Suha Computer Vision and Pattern Recognition Artificial Intelligence This paper studies continual test-time adaptation (CTTA), the task of adapting a model to constantly changing unseen domains in testing while preserving previously learned knowledge. Existing CTTA methods mostly focus on adaptation to the current test domain only, overlooking generalization to arbitrary test domains a model may face in the future. To tackle this limitation, we present a novel online test-time domain generalization framework for CTTA, dubbed TestDG. TestDG aims to learn features invariant to both current and previous test domains on the fly during testing, improving the potential for effective generalization to future domains. To this end, we propose a new model architecture and a test-time adaptation strategy dedicated to learning domain-invariant features, along with a new data structure and optimization algorithm for effectively managing information from previous test domains. TestDG achieved state of the art on four public CTTA benchmarks. Moreover, it showed superior generalization to unseen test domains. |
| title | TestDG: Test-time Domain Generalization for Continual Test-time Adaptation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2504.04981 |