# Robust Multi-View Classification under Noisy Supervision via Global Anchor Consensus

arXiv: https://arxiv.org/abs/2607.18561 · HTML: https://mlsanity.com/paper/2607.18561/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 24 of its 40 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Builds on (most cited first, 24 of 24)

- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Understanding deep learning requires rethinking generalization](https://mlsanity.com/paper/1611.03530/) (2016)
- [Co-teaching: Robust Training of Deep Neural Networks with Extremely Noisy Labels](https://mlsanity.com/paper/1804.06872/) (2018)
- [DivideMix: Learning with Noisy Labels as Semi-supervised Learning](https://mlsanity.com/paper/2002.07394/) (2020)
- [Making Deep Neural Networks Robust to Label Noise: a Loss Correction Approach](https://mlsanity.com/paper/1609.03683/) (2016)
- [Learning from Noisy Labels with Deep Neural Networks: A Survey](https://mlsanity.com/paper/2007.08199/) (2020)
- [CleanNet: Transfer Learning for Scalable Image Classifier Training with Label Noise](https://mlsanity.com/paper/1711.07131/) (2017)
- [Trusted Multi-View Classification with Dynamic Evidential Fusion](https://mlsanity.com/paper/2204.11423/) (2022)
- [On Deep Multi-View Representation Learning: Objectives and Optimization](https://mlsanity.com/paper/1602.01024/) (2016)
- [Deep Self-Learning From Noisy Labels](https://mlsanity.com/paper/1908.02160/) (2019)
- [A Survey of Multi-View Representation Learning](https://mlsanity.com/paper/1610.01206/) (2016)
- [Trusted Multi-View Classification](https://mlsanity.com/paper/2102.02051/) (2021)
- [Beyond Class-Conditional Assumption: A Primary Attempt to Combat Instance-Dependent Label Noise](https://mlsanity.com/paper/2012.05458/) (2020)
- [Deep Partial Multi-View Learning](https://mlsanity.com/paper/2011.06170/) (2020)
- [MoPro: Webly Supervised Learning with Momentum Prototypes](https://mlsanity.com/paper/2009.07995/) (2020)
- [Reliable Conflictive Multi-View Learning](https://mlsanity.com/paper/2402.16897/) (2024)
- [Deep Incomplete Multi-view Clustering with Cross-view Partial Sample and Prototype Alignment](https://mlsanity.com/paper/2303.15689/) (2023)
- [GCFAgg: Global and Cross-view Feature Aggregation for Multi-view Clustering](https://mlsanity.com/paper/2305.06799/) (2023)
- [Deep Multi-View Enhancement Hashing for Image Retrieval](https://mlsanity.com/paper/2002.00169/) (2020)
- [Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification](https://mlsanity.com/paper/2304.05165/) (2023)
- [NLPrompt: Noise-Label Prompt Learning for Vision-Language Models](https://mlsanity.com/paper/2412.01256/) (2024)
- [Trusted Multi-view Learning under Noisy Supervision](https://mlsanity.com/paper/2404.11944/) (2024)
- [Instance-dependent Noisy-label Learning with Graphical Model Based Noise-rate Estimation](https://mlsanity.com/paper/2305.19486/) (2023)

## Abstract (arXiv)

In recent years, multi-view learning has attracted increasing attention, as it integrates the complementary information of heterogeneous views. Most existing multi-view classification methods rely on accurate annotations to guarantee performance. However, noisy labels are ubiquitous in practice due to imperfect annotation, and the refinement signals that existing methods derive from models trained on such noisy supervision can gradually lose their reliability. To deal with this problem, we propose a novel Global Anchor-based Label Auditing method (GALA) for multi-view classification to resist the negative impact of noisy labels. Specifically, we construct a global anchor for each class in every view, which aggregates the samples of the whole class and thus offers a stable reference insensitive to individual predictions. Then, each view measures how close an instance is to the anchor of its observed label relative to the nearest competing anchor, and the per-view evaluations are fused with the classifier confidence into a cross-view audit score. Based on the audit scores, suspicious samples are assigned small weights, and an adaptive correction strategy rewrites a label only when the anchor-based candidate agrees with the classifier prediction. Finally, the corrected labels in turn refine the anchors and supervise noise-robust representation learning. Extensive experiments on six datasets demonstrate that GALA outperforms eight state-of-the-art methods, especially under high noise rates.