PTQ4SAM: Post-Training Quantization for Segment Anything
About
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 Integration strategy, which utilizes a mathematically equivalent sign operation to transform the bimodal distribution into a relatively easy-quantized normal distribution offline. Second, SAM encompasses diverse attention mechanisms (i.e., self-attention and two-way cross-attention), resulting in substantial variations in the post-Softmax distributions. Therefore, we introduce an Adaptive Granularity Quantization for Softmax through searching the optimal power-of-two base, which is hardware-friendly. Extensive experimental results across various vision tasks (instance segmentation, semantic segmentation and object detection), datasets and model variants show the superiority of PTQ4SAM. For example, when quantizing SAM-L to 6-bit, we achieve lossless accuracy for instance segmentation, about 0.5\% drop with theoretical 3.9$\times$ acceleration. The code is available at \url{https://github.com/chengtao-lv/PTQ4SAM}.
Related benchmarks
| Task | Dataset | Result | Rank | |
|---|---|---|---|---|
| Semantic segmentation | ADE20K (val) | mIoU33.66 | 2888 | |
| Instance Segmentation | COCO 2017 (val) | -- | 1201 | |
| Oriented Object Detection | DOTA v1.0 (test) | -- | 378 | |
| Instance Segmentation | COCO | mAP48.2 | 144 | |
| Video Object Segmentation | SA-V (val) | J&F Score70.65 | 114 | |
| Video Object Segmentation | SA-V (test) | J&F73.41 | 110 | |
| Video segmentation | DAVIS | J&F Score86.04 | 41 |