No AI summary available for this article.
Why It Matters
Test-Time Adaptation (TTA) has recently emerged as a promising strategy that allows the adaptation of pre-trained models to changing data distributions at deployment time, without access to any labels.
Provenance
Discovered via ArXiv and published by ArXiv.
Key Claims
Original description
Test-Time Adaptation (TTA) has recently emerged as a promising strategy that allows the adaptation of pre-trained models to changing data distributions at deployment time, without access to any labels. To mitigate error accumulation, researchers have widely adopted the teacher-student framework, though its long-term stability is often taken for granted. In this work, we challenge the common strategy of setting the teacher weights to an exponential moving average of the student by showing that error accumulation still occurs, although it is mostly apparent on longer sequences compared to those...
Discovered via ArXiv
Research papers and preprints from arXiv.
Publisher: arxiv.org
ID: http://arxiv.org/abs/2609.02507v1 · Indexed about 1 hour ago