AI RESEARCH

Test-Time Distillation for Continual Model Adaptation

arXiv CS.CV

ArXi:2506.02671v3 Announce Type: replace Deep neural networks often suffer performance degradation upon deployment due to distribution shifts. Continual Test-Time Adaptation (CTTA) aims to address this issue in an unsupervised manner. However, existing methods that rely on self-supervision are prone to an inherent self-referential feedback loop that amplifies initial prediction errors, leading to model drift.