AI Paper Atlas

Research map / Vision-language and multimodal / Cross-modal learning

DPL: Decoupled Prototype Learning for Enhancing Robustness of Vision-Language Transformers to Missing Modalities

Jueqing Lu, Yuanyuan Qi, Xiaohao Yang, Shuaicheng Niu, Fucai Ke, Shujie Zhou, Wei Tan, Jionghao Lin, Wray Buntine, Hamid Rezatofighi, Lan Du

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Contrastive vision-language alignment · 1 citations (OpenAlex)

This paper tried a common change: Add a contrastive loss

add prototype relational contrastive loss L_PRC to ArcFace · Hateful Memes (mixed missing 70%) · AUROC: 68.59 -> 69.31 Improved

What 1,317 accepted papers report for this change

See this change in detailMatched by the wording of each paper's own result, read by AI from the full text. Papers report gains more often than failures, so this shows what gets published, not the chance a change works.

Read the paper

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
replace FC head with DPLMaPLe · MM-IMDb (text 50% missing)F1-Macro: 54.31 -> 56.36Improved
replace FC head with DPLDCP · MM-IMDb (text 50% missing)F1-Macro: 53.62 -> 56.94Improved
replace FC head with DPLMAP · MM-IMDb (text 50% missing)F1-Macro: 53.32 -> 56.03Improved
replace FC head with DPLfrozen CLIP, no prompt tuning · UPMC Food-101 (mixed missing 90%)Accuracy: 79.44 -> 81.99Improved
replace FC head with DPLDCP · Hateful Memes (mixed missing 70%)AUROC: 64.96 -> 67.68Improved
replace FC head with DPLfrozen CLIP, no prompt tuning · Hateful Memes (image 100%/text 10%)AUROC: 63.48 -> 63.60 (text-only 10%); 66.61 -> 70.76 (image 100%/text 10% row, 90% rate)Mixed
replace FC head with DPLMAP · Hateful Memes (image 100%/text 30%, ViLT)AUROC: 62.24 -> 63.29Improved
replace FC head with DPLMAP · Hateful Memes (image 30%/text 100%, ViLT)AUROC: 54.02 -> 64.53Improved
replace FC head with DePTMAP · UPMC Food-101 (mixed missing 70%)Accuracy: 85.13 -> 84.02Hurt
replace FC head with DePTMAP · UPMC Food-101 (mixed missing 90%)Accuracy: 79.54 -> 79.97Improved
decompose prototypes into image and text components (ablation)DPL, DCP · Hateful Memes (mixed missing 70%)AUROC: 66.82 -> 68.59Improved
decompose prototypes into modality components (ablation)DPL, DCP · Hateful Memes (mixed missing 90%)AUROC: 66.36 -> 64.22 (ArcFace decomp. vs un-decomp.)Mixed

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