Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.
Towards efficient visual adaption via structural re-parameterization
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
A prompt-free dual-adapter fine-tuning method for SAM2 achieves up to 19.66% better accuracy on biomedical datasets and 87% lower compute than heavy medical SAM adaptations.
citing papers explorer
-
Visual prompting reimagined: The power of the Activation Prompts
Activation prompts on intermediate layers outperform input-level visual prompting and parameter-efficient fine-tuning in accuracy and efficiency across 29 datasets.
-
Prompt-Free and Efficient SAM2 Adaptation for Biomedical Semantic Segmentation via Dual Adapters
A prompt-free dual-adapter fine-tuning method for SAM2 achieves up to 19.66% better accuracy on biomedical datasets and 87% lower compute than heavy medical SAM adaptations.