PTQ4SAM: Post-Training Quantization for Segment Anything

arXiv:2405.03144v1 Announce Type: cross
Abstract: Segment Anything Model (SAM) has achieved impressive performance in many computer vision tasks. However, as a large-scale model, the immense memory and computation costs hinder its practical deployment. In this paper, we propose a post-training quantization (PTQ) framework for Segment Anything Model, namely PTQ4SAM. First, we investigate the inherent bottleneck of SAM quantization attributed to the bimodal distribution in post-Key-Linear activations. We analyze its characteristics from both per-tensor and per-channel perspectives, and propose a Bimodal …

arxiv cs.cv cs.lg quantization segment segment anything training type