AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

DeAR: Fine-Grained VLM Adaptation by Decomposing Attention Head Roles

Yiming Ma, Hongkun Yang, Lionel Z. Wang, Bin Chen, Weizhi Xian, Jianzhi Teng

CVPR 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 2 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
Role-based attention mask (vs shielding all deep heads) (ablation)DeAR · Base-to-novel, 11-dataset averageHarmonic mean: 80.68 -> 82.72Improved
Role-based attention mask (vs allowing all interactions) (ablation)DeAR · Base-to-novel, 11-dataset averageHarmonic mean: 80.93 -> 82.72Improved
Add self-regularization loss Lreg (ablation)DeAR (CE only) · Base-to-novel, 11-dataset averageNovel accuracy: 74.21 -> 78.45Improved
Add self-regularization loss Lreg (ablation)DeAR (CE only) · Base-to-novel, 11-dataset averageBase accuracy: 86.75 -> 85.03Hurt
Add fusion-weight regularization Lfusion (ablation)DeAR (CE+Lreg) · Base-to-novel, 11-dataset averageHarmonic mean: 81.61 -> 82.72Improved
Use DeAR instead of MMRLCLIP ViT-B/16 · Base-to-novel, 11-dataset averageHarmonic mean: 81.20 -> 82.72Improved
Use DeAR instead of MMRLCLIP ViT-B/16 · Cross-dataset (avg of 10 targets)Accuracy: 67.25 -> 67.60Improved
Use DeAR instead of TACCLIP ViT-B/16 · Domain generalization (average of 4 variants)Accuracy: 61.63 -> 61.25Hurt
Use DeAR instead of TACCLIP ViT-B/16 · Domain generalization (ImageNet-R)Accuracy: 78.50 -> 78.83Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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