# Learning What to Trust in Multimodal Learning under Noisy Supervision

arXiv: https://arxiv.org/abs/2610.11057 · HTML: https://mlsanity.com/paper/2610.11057/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 91 references that are in the map.
- First posted on arXiv 8 Oct 2026.

## Builds on (most cited first, 6 of 6)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Decoupled Weight Decay Regularization](https://mlsanity.com/paper/1711.05101/) (2017)
- [Learning with Noisy Labels Revisited: A Study Using Real-World Human Annotations](https://mlsanity.com/paper/2110.12088/) (2021)
- [FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning](https://mlsanity.com/paper/2205.07246/) (2022)
- [A Survey of Label-noise Representation Learning: Past, Present and Future](https://mlsanity.com/paper/2011.04406/) (2020)
- [MOLAR: Learning Multimodal Molecular Representations from Noisy Labels](https://mlsanity.com/paper/2606.18390/) (2026)

## Abstract (arXiv)

Multimodal classification processes and relates information from multiple modalities to achieve more accurate predictions. However, existing methods typically rely on high-quality ground-truth labels, which are difficult to obtain in real-world scenarios. While sample-selection methods for learning with noisy labels aim to identify correctly labeled examples from noisy data, traditional methods primarily focus on unimodal settings and fail to exploit multimodal information fully. This motivates us to build a more reliable noise detector in multimodal learning. To this end, we theoretically analyze the relationship between representation structure and noise detection capability. Based on this analysis, we propose REFINE, which is a multimodal label-noise detection framework that jointly uses fused and unimodal representations for label-noise detection. Specifically, REFINE constructs discriminative eigenvectors through discriminative analysis of the target and background classes and selects trusted representation spaces with better noise detection capability for each class. Within each trusted space, REFINE measures the alignment between each instance representation and the discriminative eigenvectors. It then combines the subsets selected from these spaces. The combined set provides cleaner supervision for updating the multimodal classifier, thereby reducing the influence of mislabeled examples during training and improving model generalization. Extensive experiments across diverse tasks demonstrate REFINE's superiority compared to baseline methods. The source code will be publicly available.