AI Paper Atlas

Research map / Architectures and efficiency / Quantization

BLOB-Q: Boosting Low Bit ViT Quantization via Global Optimization on Model Distortion

Wang Mark, Kaixin Xu, Xue Geng, Fen Fang, Mohamed Aly, Xulei Yang, Min Wu, Weisi Lin

ECCV 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 1 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
optimize model-level distortion instead of layer distortion (greedy local solver) (ablation)BLOB-Q · ImageNet val ViT-S 4-bittop-1 accuracy: 0.11% -> 20.52%Improved
replace the local solver with the global-optimal DP solver (ablation)BLOB-Q · ImageNet val ViT-S 4-bittop-1 accuracy: 20.52% -> 76.85%Improved
replace the local solver with the global-optimal DP solver (ablation)BLOB-Q · ImageNet val ViT-B 4-bittop-1 accuracy: 1.25% -> 82.84%Improved
replace the local solver with the global-optimal DP solver (ablation)BLOB-Q · ImageNet val DeiT-B/384 4-bittop-1 accuracy: 49.92% -> 81.64%Improved
replace the local solver with the global-optimal DP solver (ablation)BLOB-Q · ImageNet val ViT-S 6-bittop-1 accuracy: 62.87% -> 80.76%Improved
optimize model distortion instead of layer distortion (local solver) (ablation)BLOB-Q · ImageNet val DeiT-B 8-bittop-1 accuracy: 45.81% -> 80.81%Improved
increase calibration set from 32 to 512 images (ablation)BLOB-Q · ImageNet val DeiT-S 4-bittop-1 accuracy: 75.33% -> 76.13%Improved
increase calibration set from 512 to 1024 images (ablation)BLOB-Q · ImageNet val DeiT-S 6-bittop-1 accuracy: 79.65% -> 79.42%No clear effect
add BLOB-Q mixed-precision allocation on top of ERQERQ · ImageNet val ViT-B 4-bittop-1 accuracy: 76.63 -> 80.14Improved
add BLOB-Q mixed-precision allocation on top of ERQERQ · ImageNet val DeiT-S 4-bittop-1 accuracy: 72.56 -> 77.87Improved
add BLOB-Q mixed-precision allocation on top of ERQERQ · ImageNet val DeiT-B 6-bittop-1 accuracy: 81.41 -> 82.03Improved
restrict per-layer bit-width to {4,8} instead of [1,10] (ablation)BLOB-Q · ImageNet val ViT-B 6 MPtop-1 accuracy: 85.07 -> 84.26Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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