AI Paper Atlas

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

Robust Remote Sensing Image-Text Retrieval with Noisy Correspondence

Qiya Song, Yiqiang Xie, Yuan Sun, Renwei Dian, Xudong Kang

CVPR 2026 · Vision-language and multimodal › Cross-modal learning · approach: Probabilistic embeddings for cross-modal retrieval · 0 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 local contrastive learning (ablation)RRSITR · RSITMD (80% noise)mR: 33.38 -> 35.93Improved
add the multi-modal SPL module (ablation)RRSITR · RSITMD (80% noise)mR: 29.80 -> 35.93Improved
add the robust triplet loss (RTL) (ablation)RRSITR · RSITMD (80% noise)mR: 30.21 -> 35.93Improved
add all three components jointly (ablation)RRSITR · RSITMD (80% noise)mR: 32.24 -> 35.93Improved
use easy-to-hard SPL instead of hard-to-easy (ablation)RRSITR · RSITMD (80% noise)mR: 1.22 -> 35.93Improved
use self-paced weighting instead of random sample weighting (ablation)RRSITR · RSITMD (80% noise)mR: 26.52 -> 35.93Improved
keep ambiguous pairs in SPL instead of removing them (ablation)RRSITR · RSITMD (80% noise)mR: 1.10 -> 35.93Improved
use adaptive soft-margin RTL instead of fixed-margin triplet loss (ablation)RRSITR · RSITMD (80% noise)mR: 33.90 -> 35.93Improved
add local contrastive learning (ablation)RRSITR · RSITMD (80% noise)R@1 image-to-text: 15.44 -> 16.90Improved
replace the fixed-margin triplet loss with RTL (ablation)RRSITR · RSITMD (80% noise)text-to-image R@5: 39.45 -> 42.70Improved
compare RRSITR with CUP as noise rises from 20% to 80%RRSITR · RSITMDmR: 45.58 vs 38.99 at 20%; 35.93 vs 27.59 at 80%Improved
compare RRSITR with best baseline on NWPU at 80% noiseRRSITR · NWPU (80% noise)mR: 12.21 -> 32.13Improved

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