AI Paper Atlas

Research map / Architectures and efficiency / Quantization

AHCPTQ: Accurate and Hardware-Compatible Post-Training Quantization for Segment Anything Model

Wenlun Zhang, Yunshan Zhong, Shimpei Ando, Kentaro Yoshioka

ICCV 2025 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 7 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 CAG to AHCPTQ without it (HLUQ only) (ablation)SAM-L · COCO instance segmentation, YOLOX prompts, W4A4mAP: 5.7 -> 31.0Improved
add CAG to AHCPTQ without it (HLUQ only) (ablation)SAM-H · COCO instance segmentation, YOLOX prompts, W4A4mAP: 24.8 -> 35.2Improved
add HLUQ to AHCPTQ without it (CAG only) (ablation)SAM-L · COCO instance segmentation, YOLOX prompts, W4A4mAP: 22.7 -> 31.0Improved
add HLUQ to AHCPTQ without it (CAG only) (ablation)SAM-H · COCO instance segmentation, YOLOX prompts, W4A4mAP: 20.2 -> 35.2Improved
add CAG alone to baseline (ablation)SAM-L · COCO instance segmentation, YOLOX prompts, W4A4mAP: 2.5 -> 22.7Improved
add HLUQ alone to baseline (ablation)SAM-B · COCO instance segmentation, YOLOX prompts, W4A4mAP: 3.7 -> 5.7Improved
use HLUQ instead of biased log2 quantizer (ablation)SAM-H · COCO instance segmentation, YOLOX prompts, W4A4mAP: 34.3 -> 35.2Improved
use HLUQ instead of uniform quantizer (ablation)SAM-L · COCO instance segmentation, YOLOX prompts, W4A4mAP: 20.2 -> 31.0Improved
increase CAG group number from 1 (per-tensor) to 4 (ablation)SAM-B · COCO YOLOX W4A4mAP: 5.7 -> 13.4Improved
use per-channel instead of 4 groups in CAG (ablation)SAM-B · COCO YOLOX W4A4mAP: 13.4 -> 16.9Mixed
use AHCPTQ INT4 instead of FP32 acceleratorMLP block FPGA · FPGA MLP block of SAM mask decoderspeedup: 1.00× -> 7.89×Improved
replace PTQ4SAM with AHCPTQSAM-L DINO · COCO DINO W4A4mAP: 2.3 -> 36.6Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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