AI RESEARCH
AcTTA: Rethinking Test-Time Adaptation via Dynamic Activation
arXiv CS.LG
•
ArXi:2603.26096v1 Announce Type: new Test-time adaptation (TTA) aims to mitigate performance degradation under distribution shifts by updating model parameters during inference. Existing approaches have primarily framed adaptation around affine modulation, focusing on recalibrating normalization layers. This perspective, while effective, overlooks another influential component in representation dynamics: the activation function.