AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model

Yatai Ji, Junjie Wang, Yuan Gong, Lin Zhang, Yanru Zhu, Hongfa Wang, Jiaxing Zhang, Tetsuya Sakai, Yujiu Yang

CVPR 2023 · Vision-language and multimodal › Human and embodied modeling · approach: Vision-language pretraining · 44 citations (OpenAlex)

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
Represent modalities as probability distributions with PDE rather than point features (ablation)MAP · VQA2.0 test-dev, MSCOCO pretrainingaccuracy: 74.57 -> 75.01Improved
Represent modalities as probability distributions with PDE rather than point features (ablation)MAP · SNLI-VE val, MSCOCO pretrainingaccuracy: 79.42 -> 80.05Improved
Represent modalities as probability distributions with PDE rather than point features (ablation)MAP · NLVR2 dev, MSCOCO pretrainingaccuracy: 77.72 -> 78.96Improved
Add sequence-level interaction to PDE (ablation)MAP · VQA2.0 test-devaccuracy: 72.01 -> 73.35Improved
Use Softmax rather than Sigmoid+Normal in PDE (ablation)MAP · VQA2.0 test-devaccuracy: 73.34 -> 73.35Improved
Use ReLU+Normal rather than Softmax in PDE (ablation)MAP · VQA2.0 test-devaccuracy: 73.35 -> 69.70Hurt
Use ReLU²+Normal rather than Softmax in PDE (ablation)MAP · VQA2.0 test-devaccuracy: 73.35 -> 70.53Hurt
Pretrain with D-MLM, D-ITM, and D-VLC instead of random initialization (ablation)MAP · VQA2.0 test-devaccuracy: 73.35 -> 75.16Improved
Include D-MLM in distribution-based pretraining (ablation)MAP · SNLI-VE test-paccuracy: 78.54 -> 80.39Improved
Use D-MLM and D-ITM without D-VLC rather than all three objectives (ablation)MAP · NLVR2 testaccuracy: 79.47 -> 79.64Improved
Increase cross-modal transformer depth from 6 to 8 layers after pretraining (ablation)MAP · VQA2.0 test-devaccuracy: 75.16 -> 75.26Improved
Increase cross-modal transformer depth from 6 to 8 layers with random initialization (ablation)MAP · VQA2.0 test-devaccuracy: 73.35 -> 73.31No 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