AI Paper Atlas

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

Decouple Before Align: Visual Disentanglement Enhances Prompt Tuning

Fei Zhang, Tianfei Zhou, Jiangchao Yao, Ya Zhang, Ivor Wai-Hung Tsang, Yanfeng Wang

TPAMI 2025 · Vision-language and multimodal › CLIP and zero-shot · approach: Parameter-efficient visual tuning · 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
add visual triplet loss Lv (ablation)DAPT-S baseline · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: +1.44 (novel -1.21)Improved
add foreground-text alignment Lf (ablation)DAPT-S baseline · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: +1.23 (novel -1.28)Improved
add background-text alignment Lb (ablation)DAPT-S baseline · StanfordCars+ImageNet avg, base-to-novelnovel accuracy: +1.60 novel, +1.05 16-shotImproved
combine all three losses Lv, Lf, Lb (ablation)DAPT-S baseline · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: 72.71 -> 75.22Improved
combine Lv and Lf without Lb (ablation)DAPT-S baseline · StanfordCars+ImageNet avg, base-to-novelnovel accuracy: -2.24Hurt
use foreground-positive term only instead of full triplet (ablation)Lv · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: +1.03 vs +1.44Hurt
use background-negative term only instead of full triplet (ablation)Lv · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: +0.77 vs +1.44Hurt
replace hard filling with Gaussian blurring (ablation)DAPT-S · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: 75.22 -> 74.09Hurt
increase background classes from 5 to 25 (ablation)Lb only · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: 72.96 -> 73.76 (novel 72.17 -> 73.87)Improved
use SEEM mask instead of Grad-CAM mask (ablation)DAPT · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: 74.17 -> 75.22Improved
raise mask erasing rate from 0.1 to 0.7 (ablation)DAPT-S · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: 75.22 -> 73.97Hurt
add DAPT to CoOp (ablation)CoOp · StanfordCars+ImageNet avg, 16-shot16-shot accuracy: +2.85Improved

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