Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation

DO-ALL is a test-time adaptation framework that uses dataset distillation to create synthetic anchors for stable long-term model performance without retaining source data.

Hugging Face · Daily Papers ·Hyun-Kurl Jang, Jihun Kim ·

Este artigo está em destaque na seleção diária de papers do Hugging Face, curada pela comunidade de pesquisa em IA.

Autores: Hyun-Kurl Jang, Jihun Kim, Hyeokjun Kweon, Kuk-Jin Yoon

  • 0 upvotes da comunidade
  • Temas: Continual Test-Time Adaptation, Dataset Distillation, source-free adaptation, catastrophic forgetting, semantic alignment, source replay

Resumo

Resumo original (em inglês), extraído do paper:

DO-ALL is a test-time adaptation framework that uses dataset distillation to create synthetic anchors for stable long-term model performance without retaining source data.

Ler o paper completo no Hugging Face →

compartilhar: