AI Paper Atlas

Research map / Architectures and efficiency / Quantization

PQ-SAM: Post-training Quantization for Segment Anything Model

Xiaoyu Liu, Xin Ding, Lei Yu, Yuanyuan Xi, Wei Li, Zhijun Tu, jie hu, Hanting Chen, Baoqun YIN, Zhiwei Xiong

ECCV 2024 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 11 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
learn quantization step sizes and shifting and scaling sizes jointly (ablation)PQ-SAM · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.6342 -> 0.7080Improved
make step sizes learnable instead of fixed (ablation)PQ-SAM · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.0556 -> 0.6342Improved
group channels with outlier hierarchical clustering rather than per-channel parameters (ablation)PQ-SAM ADT · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.6842 -> 0.7080Improved
group channels with OHC rather than evenly sized groups (ablation)PQ-SAM ADT · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.6817 -> 0.7080Improved
add tensor-wise outlier truncating (ablation)PQ-SAM · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.6342 -> 0.6533Improved
use PQ-SAM instead of RepQ-ViT for ViT-L at W4A4SAM point prompt · SAM ViT-L BBBC038V1 (W4A4)IoU: 0.4129 -> 0.6855Improved
use PQ-SAM instead of RepQ-ViT on iShape for ViT-L at W4A4SAM point prompt · SAM ViT-L iShape (W4A4)IoU: 0.2791 -> 0.2520Hurt
use PQ-SAM instead of Percentile on iShape for ViT-H at W6A6SAM point prompt · SAM ViT-H iShape (W6A6)IoU: 0.3679 -> 0.3380Hurt
increase calibration data from 100 to 500 images (ablation)PQ-SAM · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.7080 -> 0.7120No clear effect
change truncation threshold lambda away from 10 (ablation)PQ-SAM · SAM ViT-B point prompt BBBC (W4A4)IoU: 0.7080 -> 0.6901 (lambda 6) / 0.6858 (lambda 14)Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy