AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

Parameter-Free Fine-tuning via Redundancy Elimination for Vision Foundation Models

Jiahuan Long, Tingsong Jiang, Wen Yao, Yizhe Xiong, Zhengqin Xu, Shuai Jia, Hanqing Liu, Chao Ma

AAAI 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Low-rank compression and merging · 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
replace redundant channels with effective channelsSAM ViT-B · 9 segmentation datasets (avg)mIoU: 49.14 -> 58.08Improved
replace redundant channels with effective channelsSAM ViT-H · 9 segmentation datasets (avg)mIoU: 55.54 -> 60.68Improved
replace redundant channels with effective channelsSAM2 Hiera-L · 9 segmentation datasets (avg)mIoU: 67.77 -> 73.53Improved
replace redundant channels with effective channels on in-domain VOCSAM ViT-B · VOCmIoU: 38.88 -> 56.33Improved
replace redundant channels on out-of-domain ISIC16SAM ViT-B · ISIC16mIoU: 57.33 -> 65.21Improved
replace redundant channels on top of SAM-PARSERSAM-PARSER · 9 segmentation datasets (avg)mIoU: 60.96 -> 65.39Improved
replace redundant channels on top of DoRADoRA · 9 segmentation datasets (avg)mIoU: 79.12 -> 79.92Improved
replace redundant channels on top of encoder-only tuningEncoder-only tuning · COD10KmIoU: 50.65 -> no gain ('-')No clear effect
replace redundant channels on DINOv2 ViT-S for classificationDINOv2 ViT-S · CIFARaccuracy (%): 80.41 -> 80.81Improved
replace redundant channels on DINOv2 ViT-B for depthDINOv2 ViT-B · NYUv2AbsRel: 0.110 -> 0.095Improved
zero out single channels of SAM (ablation)SAM · PerSegmIoU: 50.6 -> 52.7 (ch 216), 47.9 (ch 189)Mixed
increase number of replacement pairs (ablation)channel replacement · COCO/CAMO/KVASIR (Hiera-S/T)mIoUImproved

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