AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

SAQ-SAM: Semantically-Aligned Quantization for Segment Anything Model

Jing Zhang, Zhikai Li, Chengzhi Hu, Xuewen Liu, Qingyi Gu

AAAI 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Prompted SAM segmentation · 3 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
add Prompt-Aware Reconstruction (PAR) over PTQ4SAM-L baseline (ablation)PTQ4SAM-L · COCO instance segmentation (DINO prompts, W4A4), SAM-BmAP: 14.4 -> 30.2Improved
add PCC on top of PAR (ablation)SAQ-SAM · COCO instance segmentation (DINO prompts, W4A4), SAM-BmAP: 30.2 -> 33.8Improved
add PCC on top of PAR (ablation)SAQ-SAM · COCO instance segmentation (YOLOX prompts, W4A4), SAM-BmAP: 26.2 -> 30.3Improved
add PCC on top of PAR (ablation)SAQ-SAM · COCO instance segmentation (DINO prompts, W4A4), SAM-LmAP: 46.1 -> 46.3No clear effect
add PCC on top of PAR (ablation)SAQ-SAM · COCO instance segmentation (Faster R-CNN prompts, W4A4), SAM-LmAP: 34.6 -> 34.5No clear effect
use per-stage PAR instead of per-block QDrop reconstruction (ablation)SAQ-SAM · COCO instance segmentation (YOLOX prompts, W4A4), SAM-BmAP: 6.6 -> 26.3Improved
replace QDrop with PAR at per-stage granularity (ablation)SAQ-SAM · COCO instance segmentation (YOLOX prompts, W4A4), SAM-BmAP: 17.2 -> 26.3Improved
use per-stage rather than per-block PAR (ablation)SAQ-SAM · COCO instance segmentation (YOLOX prompts, W4A4), SAM-BmAP: 24.4 -> 26.3Improved
add PCC to QDropQDrop · COCO instance segmentation (YOLOX prompts, W4A4), SAM-BmAP: 13.3 -> 21.2Improved
add PCC to RepQ-ViTRepQ-ViT · COCO instance segmentation (YOLOX prompts, W6A6), SAM-BmAP: 14.5 -> 33.8Improved
use PCC instead of PTQ4SAM clipping with RepQ-ViTRepQ-ViT · COCO instance segmentation (YOLOX prompts, W4A4), SAM-BmAP: 0.4 -> 1.2No clear effect
add PCC clipping to PTQ4SAM-S statistic pipelinePTQ4SAM-S · COCO instance segmentation (Faster R-CNN prompts, W6A6), SAM-BmAP: 15.4 -> 29.8Improved

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