AI RESEARCH

CAR-SAM: Cross-Attention Reconstruction for Post-Training Quantization of the Segment Anything Model

arXiv CS.CV

ArXi:2605.16901v1 Announce Type: new Segment Anything Models (SAMs) are extensively used in computer vision for universal image segmentation, but deploying them on resource-constrained devices is challenging due to their high computational and memory demands. Post-