AI Paper Atlas

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

Missing Modality Prediction for Unpaired Multimodal Learning via Joint Embedding of Unimodal Models

Taesup Kim, Donggeun Kim

ECCV 2024 · Vision-language and multimodal › Cross-modal learning · approach: Multimodal fusion with missing modalities · 19 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
predict missing-modality embedding with read-only prompts instead of CLS token (ablation)unimodal-encoder framework · MM-IMDb (train 100% image/30% text)F1-Macro: 44.91 -> 48.99Improved
use prompts for feature prediction (cosine similarity of image feature prediction) (ablation)unimodal-encoder framework · MM-IMDbcosine similarity of image feature prediction: 0.4 -> 0.71Improved
add variance and covariance terms (VICReg) to invariance loss (ablation)feature predictor · MM-IMDb (complete training, text-missing)F1-Macro: 25.72 -> 40.88Improved
use stop-gradient in invariance loss (ablation)feature predictor · MM-IMDb (complete training, text-missing)F1-Macro: 25.72 -> 22.72Hurt
add read-only attention masking to prompts (ablation)prompt-based predictor · MM-IMDb (complete training, text-missing)F1-Macro: 34.72 -> 40.88Improved
increase prompt length (peak at 6)read-only prompts · MM-IMDb (complete training, text-missing)F1-MacroMixed
use BitFit instead of LN tuning, prefix tuning or adapters (ablation)unimodal encoders · MM-IMDb (complete training, text-missing)F1-Macro: 39.07 (LN) / 37.75 (prefix) -> 40.88Improved
raise VICReg coefficients from 5/5/1 to 50/50/1 (ablation)feature prediction loss · MM-IMDb (complete training)F1-Macro: 36.11 -> 40.88Improved
use larger unimodal encodersframework · complete trainingrobustness to missing modalitiesImproved
ours vs unimodal baseline when train/test missing pattern is alignedframework · Food-101 (train 30% image/100% text, test 30%/100%)accuracy: 87.44 -> 87.11No 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