AI Paper Atlas

Research map / Architectures and efficiency / Quantization

SSVQ: Unleashing the Potential of Vector Quantization with Sign-Splitting

Shuaiting Li, Juncan Deng, Chengxuan Wang, Kedong Xu, Rongtao Deng, Hong Gu, Haibin Shen, Kejie Huang

ICCV 2025 · Architectures and efficiency › Quantization · approach: Post-training weight quantization · 2 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 learnable sign bit and freezing, SSVQ instead of VQVQ · DeiT-tiny ImageNet (21x)top-1 accuracy: +12% absoluteImproved
add learnable signs instead of fixed sign (ablation)SSVQ (fixed sign) · DeiT-tiny ImageNettop-1 accuracy: +3% to 9%Improved
add iterative freezing of learnable signs (ablation)SSVQ (no freezing) · DeiT-tiny ImageNettop-1 accuracy: +5%Improved
add learnable signs plus freezing to fixed-sign baseline (ablation)SSVQ (fixed sign) · DeiT-tiny ImageNet (21x)top-1 accuracy: +14.8%Improved
use freeze interval 500 instead of 100 (ablation)SSVQ · DeiT-T (k=16,d=8)top-1 accuracy: 60.9 -> 61.90Improved
use freeze interval 500 instead of 1000 (ablation)SSVQ · DeiT-T (k=16,d=8)top-1 accuracy: 61.55 -> 61.90Improved
use majority sign voting instead of EMA criterion (ablation)SSVQ · DeiT-T (k=16,d=8)top-1 accuracy: 60.8 -> 61.90Improved
use SSVQ instead of VQVQ · VOC segmentationmIoU: 65.7 -> 67.7Improved
use SSVQ instead of VQVQ · COCO YOLOv9-Sbbox AP50:95: 30.0 -> 35.2Improved
use SSVQ instead of VQVQ · Stable Diffusion v1-4 COCO promptsFID-to-FP: 24.5 -> 13.6Improved
use SSVQ instead of VQVQ · Llama3.2-1B 2-bit Wiki2perplexity: 63.1 -> 13.9Improved
train full (codebook+BN+FC) rather than only BN+FC in conventional VQ (ablation)VQ · MobileNet-V2 ImageNettop-1 accuracy: 50.01 -> 55.27Mixed

Later papers that compared with this method

1 later accepted paper reports SSVQ as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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