AI Paper Atlas

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

Multimodal Distribution Matching for Vision-Language Dataset Distillation

Jongoh Jeong, Hoyong Kwon, Minseok Kim, Kuk-Jin Yoon

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Unimodal-to-multimodal representation transfer · 0 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
initialize synthetic data with joint-feature k-means instead of random real samples (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.6 -> 21.9Improved
initialize synthetic data with joint k-means instead of Gaussian noise (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 0.5 -> 21.9Improved
cluster on joint image-text features instead of image-only features (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.8 -> 21.9Improved
use joint k-means seeding instead of K-center seeding (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.8 -> 21.9Improved
use joint k-means seeding instead of herding seeding (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 21.5 -> 21.9Improved
use fine-tuned expert instead of pre-trained model as frozen model (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 6.8 -> 17.8Improved
use proposed angle-based multi-expert interpolation instead of fine-tuned model alone (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 17.8 -> 21.9Improved
use proposed interpolation instead of random weighted sum of pre-trained and fine-tuned (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 19.6 -> 21.9Improved
add agreement loss to InfoNCE (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.98 -> 21.02No clear effect
add discrepancy loss to InfoNCE (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.98 -> 21.53Improved
add both agreement and discrepancy losses to InfoNCE (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.98 -> 21.94Improved
use geodesic kernel instead of Laplacian RBF kernel (ablation)MDM · Flickr8k (100 pairs)mean retrieval recall: 20.3 -> 21.9Improved

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