AI Paper Atlas

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

Towards Cross-modal Backward-compatible Representation Learning for Vision-Language Models

Young Kyun Jang, Ser-nam Lim

ICCV 2025 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 6 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
add text-only pretrained projection module phi (XBT vs Base trained directly) (ablation)Base (LoRA + soft prompt) · nocaps (B32 old / L14 new) new query vs old galleryR@1 text query to image gallery: 43.48 -> 48.02Improved
add text-only pretrained projection module phi (XBT vs Base trained directly) (ablation)Base (LoRA + soft prompt) · nocaps (B32 old / L14 new) new query vs old galleryR@1 image query to text gallery: 69.78 -> 75.02Improved
use XBT instead of full fine-tuning (ablation)Full-tune · nocaps (B32 old / L14 new) new query vs old galleryR@1 image query to text gallery: 63.76 -> 75.02Improved
add soft prompt on top of LoRA-only (ablation)LoRA-only · nocaps (B32 old / L14 new) new query vs old galleryR@1 text query to image gallery: 43.40 -> 43.48Improved
add Gaussian noise during text-only pretraining (ablation)XBT · nocaps (B32 old / L14 new)R@1 text query to image gallery: 47.24 -> 48.02Improved
add Gaussian noise during text-only pretraining (ablation)XBT · nocaps (B32 old / L14 new)R@1 image query to text gallery: 73.31 -> 75.02Improved
scale up the text corpus D_T from 0.25x to 1x (ablation)XBT · nocaps (B32 old / L14 new)R@1 text query to image gallery: 46.89 -> 48.02Improved
scale up the text corpus D_T from 0.5x to 1x (ablation)XBT · nocaps (B32 old / L14 new)R@1 image query to text gallery: 73.89 -> 75.02Improved
double the supervised image-text pairs (2x D) (ablation)XBT · nocaps (B32 old / L14 new)R@1 text query to image gallery: 48.02 -> 47.63No clear effect
halve the supervised image-text pairs (0.5x D) (ablation)XBT · nocaps (B32 old / L14 new)R@1 image query to text gallery: 75.02 -> 71.69Hurt
use text-only pretraining instead of image-only pretraining (ablation)XBT · nocaps (B32 old / L14 new)R@1 text query to image gallery: 45.32 -> 48.02Improved
replace supervised data with CC3M (ablation)XBT · nocaps (B32 old / L14 new)R@1 image query to text gallery: 75.02 -> 71.33Hurt

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