Continual Test-Time Adaptation in Computer Vision: Methods, Benchmarks, and Future Directions

arXiv:2607.08164v1 Announce Type: new Abstract: Deep neural nets achieve remarkable performance when training and test data share the same distribution, but this assumption frequently breaks in real-world deployment, where data undergoes continual distributional shifts. Continual Test-Time Adaptation (CTTA) addresses this challenge by adapting pretrained models to non-stationary target distributions on-the-fly, without access to source data or labeled targets, while mitigating two critical failu...