Unraveling Batch Normalization for Realistic Test-Time Adaptation

arXiv:2312.09486v3 Announce Type: replace-cross
Abstract: While recent test-time adaptations exhibit efficacy by adjusting batch normalization to narrow domain disparities, their effectiveness diminishes with realistic mini-batches due to inaccurate target estimation. As previous attempts merely introduce source statistics to mitigate this issue, the fundamental problem of inaccurate target estimation still persists, leaving the intrinsic test-time domain shifts unresolved. This paper delves into the problem of mini-batch degradation. By unraveling batch normalization, we discover that the inexact target statistics largely stem from …

arxiv cs.cv cs.lg normalization test type