AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

TR-PTS: Task-Relevant Parameter and Token Selection for Efficient Tuning

Siqi Luo, Haoran Yang, Yi Xin, Mingyang Yi, Guangyang Wu, Guangtao Zhai, Xiaohong Liu

ICCV 2025 · Architectures and efficiency › Pruning and efficient tuning · approach: Adapter-based parameter-efficient tuning · 5 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 parameter selection (FIM, layer-wise) to linear baseline (ablation)Linear probing on ViT-B/16 · VTAB-1k dSprites/locaccuracy: 12.5 -> 85.1Improved
add token selection and merging to linear baseline (ablation)Linear probing on ViT-B/16 · VTAB-1k dSprites/locaccuracy: 12.5 -> 14.8Improved
add token selection on top of parameter selection (ablation)TR-PTS parameter selection · VTAB-1k dSprites/locaccuracy: 85.1 -> 87.7Improved
add token selection on top of parameter selection (ablation)TR-PTS parameter selection · VTAB-1k Flower102accuracy: 99.4 -> 99.5Improved
add token selection on top of parameter selection (ablation)TR-PTS parameter selection · VTAB-1k Sun397accuracy: 54.2 -> 54.5Improved
add parameter selection on top of token selection (ablation)TR-PTS token selection · VTAB-1k Sun397accuracy: 51.2 -> 54.5Improved
place token selection in sparse-parameter layers instead of dense layers (ratio 0.95) (ablation)TR-PTS · VTAB-1k dSprites/locaccuracy: 85.2 -> 87.7Improved
place token selection in sparse-parameter layers instead of random layers (ratio 0.95) (ablation)TR-PTS · VTAB-1k Patch Camelyonaccuracy: 87.9 -> 88.1Improved
lower token selection ratio from 0.95 to 0.8 in sparse layers (ablation)TR-PTS · VTAB-1k Sun397accuracy: 54.5 -> 52.9Hurt
lower token selection ratio from 0.95 to 0.8 in sparse layers (ablation)TR-PTS · VTAB-1k dSprites/locaccuracy: 87.7 -> 86.0Hurt
TR-PTS versus GPS (gradient-based parameter selection)TR-PTS · VTAB-1k (19 tasks)mean accuracy: 75.18 -> 75.92Improved
TR-PTS versus GPSTR-PTS · FGVC (5 datasets)mean accuracy: 91.78 -> 91.94Improved

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