# Decoupled Mixup for Generalized Visual Recognition

arXiv: https://arxiv.org/abs/2210.14783 · HTML: https://mlsanity.com/paper/2210.14783/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 33 references that are in the map.
- First posted on arXiv 26 Oct 2022.

## Builds on (most cited first, 26 of 26)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Densely Connected Convolutional Networks](https://mlsanity.com/paper/1608.06993/) (2016)
- [mixup: Beyond Empirical Risk Minimization](https://mlsanity.com/paper/1710.09412/) (2017)
- [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)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization](https://mlsanity.com/paper/1703.06868/) (2017)
- [AugMix: A Simple Data Processing Method to Improve Robustness and Uncertainty](https://mlsanity.com/paper/1912.02781/) (2019)
- [Domain Generalization with MixStyle](https://mlsanity.com/paper/2104.02008/) (2021)
- [Learning to Generate Novel Domains for Domain Generalization](https://mlsanity.com/paper/2007.03304/) (2020)
- [A Fourier-based Framework for Domain Generalization](https://mlsanity.com/paper/2105.11120/) (2021)
- [Puzzle Mix: Exploiting Saliency and Local Statistics for Optimal Mixup](https://mlsanity.com/paper/2009.06962/) (2020)
- [Deep Domain-Adversarial Image Generation for Domain Generalisation](https://mlsanity.com/paper/2003.06054/) (2020)
- [How Does Mixup Help With Robustness and Generalization?](https://mlsanity.com/paper/2010.04819/) (2020)
- [MixUp as Locally Linear Out-Of-Manifold Regularization](https://mlsanity.com/paper/1809.02499/) (2018)
- [Deep Stable Learning for Out-Of-Distribution Generalization](https://mlsanity.com/paper/2104.07876/) (2021)
- [Efficient Domain Generalization via Common-Specific Low-Rank Decomposition](https://mlsanity.com/paper/2003.12815/) (2020)
- [NICO++: Towards Better Benchmarking for Domain Generalization](https://mlsanity.com/paper/2204.08040/) (2022)
- [Cross Language Image Matching for Weakly Supervised Semantic Segmentation](https://mlsanity.com/paper/2203.02668/) (2022)
- [Towards Unsupervised Domain Generalization](https://mlsanity.com/paper/2107.06219/) (2021)
- [Online Refinement of Low-level Feature Based Activation Map for Weakly Supervised Object Localization](https://mlsanity.com/paper/2110.05741/) (2021)
- [Towards Domain Generalization in Object Detection](https://mlsanity.com/paper/2203.14387/) (2022)
- [Group-wise Inhibition based Feature Regularization for Robust Classification](https://mlsanity.com/paper/2103.02152/) (2021)
- [FRT-PAD: Effective Presentation Attack Detection Driven by Face Related Task](https://mlsanity.com/paper/2111.11046/) (2021)
- [Robust Representation via Dynamic Feature Aggregation](https://mlsanity.com/paper/2205.07466/) (2022)

## Built on by (most cited first, 1 of 1)

- [NegVSR: Augmenting Negatives for Generalized Noise Modeling in Real-World Video Super-Resolution](https://mlsanity.com/paper/2305.14669/) (2023)

## Abstract (arXiv)

Convolutional neural networks (CNN) have demonstrated remarkable performance when the training and testing data are from the same distribution. However, such trained CNN models often largely degrade on testing data which is unseen and Out-Of-the-Distribution (OOD). To address this issue, we propose a novel "Decoupled-Mixup" method to train CNN models for OOD visual recognition. Different from previous work combining pairs of images homogeneously, our method decouples each image into discriminative and noise-prone regions, and then heterogeneously combines these regions of image pairs to train CNN models. Since the observation is that noise-prone regions such as textural and clutter backgrounds are adverse to the generalization ability of CNN models during training, we enhance features from discriminative regions and suppress noise-prone ones when combining an image pair. To further improve the generalization ability of trained models, we propose to disentangle discriminative and noise-prone regions in frequency-based and context-based fashions. Experiment results show the high generalization performance of our method on testing data that are composed of unseen contexts, where our method achieves 85.76% top-1 accuracy in Track-1 and 79.92% in Track-2 in the NICO Challenge. The source code is available at https://github.com/HaozheLiu-ST/NICOChallenge-OOD-Classification.