Research map / Label-efficient and robust learning / Noisy labels
RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval
Yanglin Feng, Hongyuan Zhu, Dezhong Peng, Xi Peng, Peng Hu
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 changed | Where | Measured | Effect |
|---|---|---|---|
| Use RONO instead of MRL | 2D-3D cross-modal retrieval · RGB-D object, symmetric noise 0.8 | mAP: 0.493 -> 0.703 | Improved |
| Use RONO instead of MRL | 2D-3D cross-modal retrieval · 3D MNIST, symmetric noise 0.8 | mAP: 0.785 -> 0.831 | Improved |
| Use RONO instead of MRL | 2D-3D cross-modal retrieval · ModelNet10, symmetric noise 0.8 | mAP: 0.832 -> 0.836 | Improved |
| Use RONO instead of MRL | 2D-3D cross-modal retrieval · ModelNet40, symmetric noise 0.8 | mAP: 0.818 -> 0.823 | Improved |
| Add robust RDC loss rather than vanilla L′rdc (ablation) | RONO · 3D MNIST, symmetric noise 0.8 | mAP: 0.342 -> 0.831 | Improved |
| Add multimodal gap loss Lmg (ablation) | RONO · 3D MNIST, Image→Point Cloud, symmetric noise 0.8 | mAP: 0.675 -> 0.831 | Improved |
| Add common representations classification loss Lcrc (ablation) | RONO · 3D MNIST, Image→Point Cloud, symmetric noise 0.8 | mAP: 0.615 -> 0.831 | Improved |
| Add robust discriminative center loss Lrdc (ablation) | RONO · 3D MNIST, Image→Point Cloud, symmetric noise 0.8 | mAP: 0.709 -> 0.831 | Improved |
Later papers that compared with this method
1 later accepted paper reports RONO as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- Neighbor-aware Instance Refining with Noisy Labels for Cross-Modal Retrieval (AAAI 2026 · better on 3 of 3 shared results)
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- DREAM: Decoupled Discriminative Learning with Bigraph-aware Alignment for Semi-supervised 2D-3D Cross-modal Retrieval (AAAI 2025 · similarity 0.89)
- Fuzzy Multimodal Learning for Trusted Cross-modal Retrieval (CVPR 2025 · similarity 0.86)
- RoDA: Robust Domain Alignment for Cross-Domain Retrieval Against Label Noise (AAAI 2025 · similarity 0.86)
- Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval (CVPR 2024 · similarity 0.85)
- Mitigating Noisy Correspondence by Geometrical Structure Consistency Learning (CVPR 2024 · similarity 0.85)
- TSVC: Tripartite Learning with Semantic Variation Consistency for Robust Image-Text Retrieval (AAAI 2025 · similarity 0.85)
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.
