New TTA memory policy boosts model adaptation with diversity

Researchers have developed a new approach to test-time adaptation (TTA) for machine learning models, focusing on how memory policies influence adaptation to distribution shifts. Their work introduces Guided Observational Test-Time Adaptation (GOTTA), which prioritizes intra-class diversity in memory selection alongside class balance. This diversity-aware memory management proves most effective under limited memory and challenging non-i.i.d. data streams, enhancing adaptation robustness. AI

Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →

IMPACT Enhances model robustness to distribution shifts, particularly under memory constraints.

RANK_REASON Academic paper introducing a novel method for test-time adaptation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CV →

• GOTTA
• Test-time adaptation (TTA)

• paper
• model release