AI Paper Atlas

Research map / Architectures and efficiency / Quantization

Efficient Quantization-Aware Adaptation for Visual Foundation Models

Yinglong Li, Xiaoyu Liu, Yutong Liu, Yueyi Zhang, Zhiwei Xiong

ECCV 2026 · Architectures and efficiency › Quantization · approach: Post-training quantization of ViTs · 0 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
split a sub-network side adapter and exclude the frozen backbone from the computation graph (ablation)EQuA on SAM-H W4A4 · SAM-H training memorytraining memory (GB): 67.6 -> 18.6Improved
add gradient recomputation through the frozen backbone (ablation)EQuA SSA · Kvasir (SAM-H, W4A4)S-measure: 0.881 -> 0.910Improved
add LoRA to SSA linear layers (ablation)EQuA · Kvasir (SAM-H, W4A4)S-measure: 0.910 -> 0.906; params 29.90M -> 7.67MNo clear effect
add block-wise activation quantizer fine-tuning (BAQF) (ablation)EQuA · Kvasir (SAM-H, W4A4)S-measure: 0.906 -> 0.915Improved
perform BAQF (K=10 vs none) (ablation)EQuA · Leaf (SAM-H, W4A4)mIoU: 0.699 -> 0.709Improved
increase SSA dimension 32 to 64 (ablation)EQuA · Kvasir (SAM-H, W4A4)E-measure: 0.933 -> 0.947Improved
increase SSA dimension 64 to 128 (ablation)EQuA · Kvasir (SAM-H, W4A4)E-measure: 0.947 -> 0.943No clear effect
increase LoRA rank 4 to 8 (ablation)EQuA · Kvasir (SAM-H, W4A4)S-measure: 0.915 -> 0.919No clear effect
increase BAQF iterations 100 to 200 (ablation)EQuA · Leaf (SAM-H, W4A4)mIoU: 0.709 -> 0.710No clear effect
EQuA vs QST under W4A4 (merged adapter, quantizer tuning)SAM-H · Leaf (SAM-H, W4A4)mIoU: 0.656 -> 0.709Improved
EQuA vs PEQA on memory, with similar accuracySAM-H W4A4 · SAM-H training memorytraining memory (GB): 69.4 -> 18.5Improved
EQuA vs PEQA on accuracyViT-B W4A4 · VTAB-1K Group Averagetop-1 accuracy: 72.9 -> 72.0Hurt

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