# Harnessing Hard Mixed Samples with Decoupled Regularizer

arXiv: https://arxiv.org/abs/2203.10761 · HTML: https://mlsanity.com/paper/2203.10761/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 73 references that are in the map.
- First posted on arXiv 21 Mar 2022.

## Builds on (most cited first, 30 of 44)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Training data-efficient image transformers & distillation through attention](https://mlsanity.com/paper/2012.12877/) (2020)
- [Wide Residual Networks](https://mlsanity.com/paper/1605.07146/) (2016)
- [CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Features](https://mlsanity.com/paper/1905.04899/) (2019)
- [Aggregated Residual Transformations for Deep Neural Networks](https://mlsanity.com/paper/1611.05431/) (2016)
- [FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidence](https://mlsanity.com/paper/2001.07685/) (2020)
- [Fine-Grained Visual Classification of Aircraft](https://mlsanity.com/paper/1306.5151/) (2013)
- [MixMatch: A Holistic Approach to Semi-Supervised Learning](https://mlsanity.com/paper/1905.02249/) (2019)
- [Unsupervised Data Augmentation for Consistency Training](https://mlsanity.com/paper/1904.12848/) (2019)
- [Large Batch Optimization for Deep Learning: Training BERT in 76 minutes](https://mlsanity.com/paper/1904.00962/) (2019)
- [FlexMatch: Boosting Semi-Supervised Learning with Curriculum Pseudo Labeling](https://mlsanity.com/paper/2110.08263/) (2021)
- [Intriguing Properties of Vision Transformers](https://mlsanity.com/paper/2105.10497/) (2021)
- [DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition](https://mlsanity.com/paper/1310.1531/) (2013)
- [Hard Negative Mixing for Contrastive Learning](https://mlsanity.com/paper/2010.01028/) (2020)
- [A Downsampled Variant of ImageNet as an Alternative to the CIFAR datasets](https://mlsanity.com/paper/1707.08819/) (2017)
- [ResNet strikes back: An improved training procedure in timm](https://mlsanity.com/paper/2110.00476/) (2021)
- [ReMixMatch: Semi-Supervised Learning with Distribution Alignment and Augmentation Anchoring](https://mlsanity.com/paper/1911.09785/) (2019)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Explicit Inductive Bias for Transfer Learning with Convolutional Networks](https://mlsanity.com/paper/1802.01483/) (2018)
- [CoMatch: Semi-supervised Learning with Contrastive Graph Regularization](https://mlsanity.com/paper/2011.11183/) (2020)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)

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

- [Semi-supervised learning made simple with self-supervised clustering](https://mlsanity.com/paper/2306.07483/) (2023)
- [A Survey on Mixup Augmentations and Beyond](https://mlsanity.com/paper/2409.05202/) (2024)
- [DLME: Deep Local-flatness Manifold Embedding](https://mlsanity.com/paper/2207.03160/) (2022)
- [SemiReward: A General Reward Model for Semi-supervised Learning](https://mlsanity.com/paper/2310.03013/) (2023)
- [SUMix: Mixup with Semantic and Uncertain Information](https://mlsanity.com/paper/2407.07805/) (2024)
- [SMMix: Self-Motivated Image Mixing for Vision Transformers](https://mlsanity.com/paper/2212.12977/) (2022)
- [MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding](https://mlsanity.com/paper/2510.23479/) (2025)
- [StarLKNet: Star Mixup with Large Kernel Networks for Palm Vein Identification](https://mlsanity.com/paper/2405.12721/) (2024)
- [Short-Long Convolutions Help Hardware-Efficient Linear Attention to Focus on Long Sequences](https://mlsanity.com/paper/2406.08128/) (2024)
- [SupReMix: Supervised Contrastive Learning for Medical Imaging Regression with Mixup](https://mlsanity.com/paper/2309.16633/) (2023)
- [Acoustic Feature Mixup for Balanced Multi-aspect Pronunciation Assessment](https://mlsanity.com/paper/2406.15723/) (2024)
- [S2-FracMix: Label-Preserving Self-Saliency Mixup Augmentation](https://mlsanity.com/paper/2606.25784/) (2026)
- [Enhancing Protein Predictive Models via Proteins Data Augmentation: A Benchmark and New Directions](https://mlsanity.com/paper/2403.00875/) (2024)
- [PaperFit: Vision-in-the-Loop Typesetting Optimization for Scientific Documents](https://mlsanity.com/paper/2605.10341/) (2026)
- [InstructMixup: Instruction-Guided Salient Patch Editing for Robust Data Augmentation](https://mlsanity.com/paper/2607.19324/) (2026)
- [GoogLe2Net: Going Transverse with Convolutions](https://mlsanity.com/paper/2301.00424/) (2023)
- [OA-CutMix: Correcting the Label Bias of CutMix](https://mlsanity.com/paper/2606.04820/) (2026)

## Abstract (arXiv)

Mixup is an efficient data augmentation approach that improves the generalization of neural networks by smoothing the decision boundary with mixed data. Recently, dynamic mixup methods have improved previous static policies effectively (e.g., linear interpolation) by maximizing target-related salient regions in mixed samples, but excessive additional time costs are not acceptable. These additional computational overheads mainly come from optimizing the mixed samples according to the mixed labels. However, we found that the extra optimizing step may be redundant because label-mismatched mixed samples are informative hard mixed samples for deep models to localize discriminative features. In this paper, we thus are not trying to propose a more complicated dynamic mixup policy but rather an efficient mixup objective function with a decoupled regularizer named Decoupled Mixup (DM). The primary effect is that DM can adaptively utilize those hard mixed samples to mine discriminative features without losing the original smoothness of mixup. As a result, DM enables static mixup methods to achieve comparable or even exceed the performance of dynamic methods without any extra computation. This also leads to an interesting objective design problem for mixup training that we need to focus on both smoothing the decision boundaries and identifying discriminative features. Extensive experiments on supervised and semi-supervised learning benchmarks across seven datasets validate the effectiveness of DM as a plug-and-play module. Source code and models are available at https://github.com/Westlake-AI/openmixup