analiza aiqbench
TestDG introduces a novel framework for continual test-time adaptation that learns domain-invariant features during inference, addressing the critical limitation of existing methods which fail to generalize to future unseen domains. By integrating prototype selection and update mechanisms into its architecture, this approach achieves state-of-the-art performance on multiple benchmarks while maintaining knowledge from previous tasks. This advancement is significant for deploying robust AI models in dynamic real-world environments where data distributions shift continuously over time.
TestDG: Test-time Domain Generalization for Continual Test-time Adaptation
arXiv:2504.04981v3 Announce Type: replace-cross Abstract: 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 prototype selection and update mechanisms 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.
Abstract: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 prototype selection and update mechanisms 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.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2504.04981 [cs.CV]
(or arXiv:2504.04981v3 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2504.04981 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 247 cuvinte
Subiecte conexe
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
Game Design Creativity evals
LessWrong · 12 oct. 2026
Runway’s WorldPrompt and the Engineering of Real-Time Worlds
Latent Space · 25 sept. 2026
Microsoft’s AI chief says superintelligence is near, but won’t take your job
The Verge · 8 iun. 2026