AI Paper Atlas

Research map / Architectures and efficiency / Pruning and efficient tuning

EffiDINO: Task-Specific Model Pruning via Gram Anchoring Subspace Consistency

Jianjian Yin, Liulei Li, Tao Chen, Yi Chen, Yazhou Yao, Wenguan Wang

ECCV 2026 · Architectures and efficiency › Pruning and efficient tuning · approach: Structured network pruning

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 basis-agnostic constraint, residual constraint and task-specific adaptation to the dense-alignment baseline (ablation)Cut-ViT · ADE20K (20% sparsity)mIoU: 48.4 -> 49.7Improved
add spatial and channel gram anchoring to the baseline (ablation)Cut-ViT · ADE20K (20% sparsity)mIoU: 48.4 -> 50.0Improved
use spectral entropy weighting instead of static weighting (ablation)Cut-ViT · COCO detection (30% sparsity)mAP: 47.9 -> 48.6Improved
use spectral entropy weighting instead of static weighting (ablation)Cut-ViT · DAVIS-2017 VOS (30% sparsity)(J&F)m / Jm / Fm: 58.8 / 57.2 / 60.3 -> 59.4 / 58.0 / 60.8Improved
use spectral entropy weighting instead of static weighting (ablation)Cut-ViT · FG3DCar / JODS / SBD matching (30% sparsity)PCK@0.05: 70.2 / 55.5 / 37.3 -> 70.8 / 56.3 / 37.9Improved
replace MSE alignment with basis-invariant subspace consistency (ablation)Cut-ViT · COCO detectionmAP: 54.7 -> 55.7Improved
add MSE alignment to the baseline (ablation)Cut-ViT baseline · COCO detectionmAP: 54.3 -> 54.7Improved
increase principal components K from 96 to 192 (ablation)Cut-ViT · ADE20K (20% sparsity)mIoU: 49.6 -> 50.0Improved
increase principal components K from 192 to 500 (ablation)Cut-ViT · ADE20K (20% sparsity)mIoU: 50.0 -> 50.2No clear effect
prune on the target dataset instead of ImageNet (ablation)SNOWS · DAVIS-2017 VOS (30% sparsity)(J&F)m: 52.9 -> 53.4No clear effect
prune on the target dataset instead of ImageNet (ablation)SnapViT · DAVIS-2017 VOS (30% sparsity)(J&F)m: 56.0 -> 56.4No clear effect
apply Cut-ViT instead of SnapViT on a SAM backboneSAM · Promptable segmentation (30% sparsity)score: 68.6 -> 71.3Improved

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