Proposes dynamic token re-weighting during target-domain fine-tuning to mitigate exacerbated attention sink in source-free CDFSL, achieving SOTA on four benchmarks.
Compositional few-shot class-incremental learning.arXiv preprint arXiv:2405.17022, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
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.