AI Paper Atlas

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

Calibrating Multimodal Learning

Huan Ma, Qingyang Zhang, Changqing Zhang, Bingzhe Wu, Huazhu Fu, Joey Tianyi Zhou, Qinghua Hu

ICML 2023 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 10 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
Add CML regularization to CPM-Nets (ablation)Type I multimodal classifier · YaleBVRR (%): 39.15±4.97 -> 15.05±1.12Improved
Add CML regularization to CPM-Nets (ablation)Type I multimodal classifier · TUANDROMDAccuracy: 84.66±0.43 -> 85.20±0.81Improved
Add CML regularization to MIWAE (ablation)Type II multimodal classifier · TUANDROMDAccuracy: 86.32±0.85 -> 88.69±0.99Improved
Add CML regularization to MMTM (ablation)Type III multimodal classifier · NYUD2Accuracy: 66.89±0.85 -> 68.09±0.68Improved
Add CML regularization to MMTM (ablation)Type III multimodal classifier · SUN-RGBDAccuracy: 62.11±0.31 -> 62.78±0.32Improved
Add CML regularization (ablation)CPM-Nets, modality 1 corrupted · CUB, Gaussian noise ε=0.5Accuracy: 71.17±9.14 -> 81.11±4.37Improved
Add CML regularization (ablation)CPM-Nets, modalities 1 and 2 corrupted · CUB, Gaussian noise ε=0.5Accuracy: 72.50±11.14 -> 81.39±6.43Improved
Use a strict confidence-difference penalty instead of penalizing only confidence increases after modality removal (ablation)CML multimodal classifier · Partial-modality confidence estimationPredictive confidenceHurt
Add CML regularization (ablation)Type I multimodal classifier · CUBNLL: 20.49±0.30 -> 20.53±0.46No clear effect
Add CML regularization (ablation)Type I multimodal classifier · CUBAccuracy: 87.00±4.36 -> 88.33±4.05No clear effect
Add CML regularization (ablation)Type II multimodal classifier · CUBAccuracy: 92.33±1.11 -> 94.50±1.71No clear effect

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