RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation 事件

RepSAM: Bridging Foundation Models to Robotic Vision via Representation-Guided Adaptation arXiv:2605.25495v1 Announce Type: cross Abstract: Robotic perception in unstructured environments remains challenging despite the zero-shot capabilities of foundation models such as SAM. This work attributes performance degradation to non-uniform representation shifts across transformer layers: shallow layers exhibit substantial domain gaps (CKA 0.7). Based on this observation, we propose RepSAM, a repres