Proposes Adaptive Tail-Head Alignment (ATHA) that breaks alignment for low-similarity 'tail tokens' in CLIP to boost source-free cross-domain few-shot learning.
Random registers for cross-domain few-shot learning.arXiv preprint arXiv:2506.02843, 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2representative citing papers
Proposes dynamic token re-weighting during target-domain fine-tuning to mitigate exacerbated attention sink in source-free CDFSL, achieving SOTA on four benchmarks.
citing papers explorer
-
Improving CLIP Adaptation by Breaking Tail Alignment for Source-Free Cross-Domain Few-Shot Learning
Proposes Adaptive Tail-Head Alignment (ATHA) that breaks alignment for low-similarity 'tail tokens' in CLIP to boost source-free cross-domain few-shot learning.
-
Addressing Exacerbated Attention Sink for Source-Free Cross-Domain Few-Shot Learning
Proposes dynamic token re-weighting during target-domain fine-tuning to mitigate exacerbated attention sink in source-free CDFSL, achieving SOTA on four benchmarks.