BA-SAM: Scalable Bias-Mode Attention Mask for Segment Anything Model

arXiv:2401.02317v3 Announce Type: replace
Abstract: In this paper, we address the challenge of image resolution variation for the Segment Anything Model (SAM). SAM, known for its zero-shot generalizability, exhibits a performance degradation when faced with datasets with varying image sizes. Previous approaches tend to resize the image to a fixed size or adopt structure modifications, hindering the preservation of SAM's rich prior knowledge. Besides, such task-specific tuning necessitates a complete retraining of the model, which is cost-expensive and unacceptable for …

abstract arxiv attention bias challenge cs.cv datasets image paper performance sam scalable segment segment anything segment anything model type variation zero-shot