# Suppressing Mislabeled Data via Grouping and Self-Attention

arXiv: https://arxiv.org/abs/2010.15603 · HTML: https://mlsanity.com/paper/2010.15603/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 29 Oct 2020.

## Built on by (most cited first, 17 of 17)

- [Adaptive Integration of Partial Label Learning and Negative Learning for Enhanced Noisy Label Learning](https://mlsanity.com/paper/2312.09505/) (2023)
- [A Short Survey on Importance Weighting for Machine Learning](https://mlsanity.com/paper/2403.10175/) (2024)
- [An Efficient Training Approach for Very Large Scale Face Recognition](https://mlsanity.com/paper/2105.10375/) (2021)
- [Foster Adaptivity and Balance in Learning with Noisy Labels](https://mlsanity.com/paper/2407.02778/) (2024)
- [Unlocking the Power of Open Set : A New Perspective for Open-Set Noisy Label Learning](https://mlsanity.com/paper/2305.04203/) (2023)
- [A Systematic Review of Generalization Research in Medical Image Classification](https://mlsanity.com/paper/2403.12167/) (2024)
- [SecureSense: Defending Adversarial Attack for Secure Device-Free Human Activity Recognition](https://mlsanity.com/paper/2204.01560/) (2022)
- [Learning with Imbalanced Noisy Data by Preventing Bias in Sample Selection](https://mlsanity.com/paper/2402.11242/) (2024)
- [Reliable Label Correction is a Good Booster When Learning with Extremely Noisy Labels](https://mlsanity.com/paper/2205.00186/) (2022)
- [Label-noise-tolerant medical image classification via self-attention and self-supervised learning](https://mlsanity.com/paper/2306.09718/) (2023)
- [GenKL: An Iterative Framework for Resolving Label Ambiguity and Label Non-conformity in Web Images Via a New Generalized KL Divergence](https://mlsanity.com/paper/2307.09810/) (2023)
- [Shuffle Augmentation of Features from Unlabeled Data for Unsupervised Domain Adaptation](https://mlsanity.com/paper/2201.11963/) (2022)
- [Open set label noise learning with robust sample selection and margin-guided module](https://mlsanity.com/paper/2501.04269/) (2025)
- [Adaptively Point-weighting Curriculum Learning](https://mlsanity.com/paper/2505.01665/) (2025)
- [CAFE: Learning to Condense Dataset by Aligning Features](https://mlsanity.com/paper/2203.01531/) (2022)
- [Group Benefits Instances Selection for Data Purification](https://mlsanity.com/paper/2403.15694/) (2024)
- [Combating Noisy Labels through Fostering Self- and Neighbor-Consistency](https://mlsanity.com/paper/2601.12795/) (2026)

## Abstract (arXiv)

Deep networks achieve excellent results on large-scale clean data but degrade significantly when learning from noisy labels. To suppressing the impact of mislabeled data, this paper proposes a conceptually simple yet efficient training block, termed as Attentive Feature Mixup (AFM), which allows paying more attention to clean samples and less to mislabeled ones via sample interactions in small groups. Specifically, this plug-and-play AFM first leverages a textitgroup-to-attend module to construct groups and assign attention weights for group-wise samples, and then uses a textitmixup module with the attention weights to interpolate massive noisy-suppressed samples. The AFM has several appealing benefits for noise-robust deep learning. (i) It does not rely on any assumptions and extra clean subset. (ii) With massive interpolations, the ratio of useless samples is reduced dramatically compared to the original noisy ratio. (iii) pxjIt jointly optimizes the interpolation weights with classifiers, suppressing the influence of mislabeled data via low attention weights. (iv) It partially inherits the vicinal risk minimization of mixup to alleviate over-fitting while improves it by sampling fewer feature-target vectors around mislabeled data from the mixup vicinal distribution. Extensive experiments demonstrate that AFM yields state-of-the-art results on two challenging real-world noisy datasets: Food101N and Clothing1M. The code will be available at https://github.com/kaiwang960112/AFM.