AI Paper Atlas

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

Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models

Biao Chen, Lin Zuo, Mengmeng Jing, Kunbin He, Yuchen Wang

AAAI 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
add importance weighted token dropout (IWTD) (ablation)DroPLe baseline · Base-to-novel (11 datasets avg)HM: 79.44 -> 81.17Improved
add vanilla dropout p=0.5 (ablation)DroPLe baseline · Base-to-novel (11 datasets avg)HM: 79.44 -> 77.81Hurt
add vanilla dropout p=0.3 (ablation)DroPLe baseline · Base-to-novel (11 datasets avg)HM: 79.44 -> 78.73Hurt
add dropblock (ablation)DroPLe baseline · Base-to-novel (11 datasets avg)HM: 79.44 -> 77.94Hurt
replace D_KL+L1 consistency with residual entropy regularization (ablation)DroPLe with IWTD · Base-to-novel (11 datasets avg)HM: 81.46 -> 82.10Improved
replace cosine consistency with residual entropy regularization (ablation)DroPLe with IWTD · Base-to-novel (11 datasets avg)HM: 81.37 -> 82.10Improved
add class attention score S_cls to S_self (ablation)DroPLe · Base-to-novel (11 datasets avg)HM: 80.66 -> 81.14Improved
add cross-modal attention score S_cross (ablation)DroPLe · Base-to-novel (11 datasets avg)HM: 81.14 -> 82.10Improved
use linear instead of non-linear residual formulation (ablation)DroPLe · Base-to-novel (11 datasets avg)HM: 80.89 -> 82.10Improved
use dropout range 10-50% instead of 20-70% (ablation)DroPLe · Base-to-novel (11 datasets avg)HM: 81.81 -> 82.10Improved
increase bridge tokens from 16 to 64 (ablation)DroPLe · Base-to-novel (11 datasets avg)HM: 81.90 -> 82.10Improved
vary lambda_0 from 0.05 to 0.10 (ablation)DroPLe · Base-to-novel (11 datasets avg)HM: 82.08 -> 82.10No clear effect

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