# Permuted AdaIN: Reducing the Bias Towards Global Statistics in Image Classification

arXiv: https://arxiv.org/abs/2010.05785 · HTML: https://mlsanity.com/paper/2010.05785/

## Key facts

- Cited by 63 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Oct 2020.

## Built on by (most cited first, 30 of 63)

- [SWAD: Domain Generalization by Seeking Flat Minima](https://mlsanity.com/paper/2102.08604/) (2021)
- [Domain Generalization by Mutual-Information Regularization with Pre-trained Models](https://mlsanity.com/paper/2203.10789/) (2022)
- [Uncertainty Modeling for Out-of-Distribution Generalization](https://mlsanity.com/paper/2202.03958/) (2022)
- [Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing](https://mlsanity.com/paper/2203.05340/) (2022)
- [Feature Alignment and Uniformity for Test Time Adaptation](https://mlsanity.com/paper/2303.10902/) (2023)
- [Optimizing Relevance Maps of Vision Transformers Improves Robustness](https://mlsanity.com/paper/2206.01161/) (2022)
- [Leveraging Vision-Language Models for Improving Domain Generalization in Image Classification](https://mlsanity.com/paper/2310.08255/) (2023)
- [PASTA: Proportional Amplitude Spectrum Training Augmentation for Syn-to-Real Domain Generalization](https://mlsanity.com/paper/2212.00979/) (2022)
- [Feature-based Style Randomization for Domain Generalization](https://mlsanity.com/paper/2106.03171/) (2021)
- [Flatness-Aware Minimization for Domain Generalization](https://mlsanity.com/paper/2307.11108/) (2023)
- [Semantic Segmentation in Art Paintings](https://mlsanity.com/paper/2203.03238/) (2022)
- [Style-Hallucinated Dual Consistency Learning: A Unified Framework for Visual Domain Generalization](https://mlsanity.com/paper/2212.09068/) (2022)
- [StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis](https://mlsanity.com/paper/2312.10741/) (2023)
- [Contrastive ACE: Domain Generalization Through Alignment of Causal Mechanisms](https://mlsanity.com/paper/2106.00925/) (2021)
- [Mix and Reason: Reasoning over Semantic Topology with Data Mixing for Domain Generalization](https://mlsanity.com/paper/2210.07571/) (2022)
- [Adversarial Style Augmentation for Domain Generalization](https://mlsanity.com/paper/2301.12643/) (2023)
- [Modality-Agnostic Debiasing for Single Domain Generalization](https://mlsanity.com/paper/2303.07123/) (2023)
- [Back-to-Bones: Rediscovering the Role of Backbones in Domain Generalization](https://mlsanity.com/paper/2209.01121/) (2022)
- [TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers](https://mlsanity.com/paper/2105.03906/) (2021)
- [Test-Time Style Shifting: Handling Arbitrary Styles in Domain Generalization](https://mlsanity.com/paper/2306.04911/) (2023)
- [Controlling Neural Collapse Enhances Out-of-Distribution Detection and Transfer Learning](https://mlsanity.com/paper/2502.10691/) (2025)
- [Domain Generalization with Correlated Style Uncertainty](https://mlsanity.com/paper/2212.09950/) (2022)
- [Cross Contrasting Feature Perturbation for Domain Generalization](https://mlsanity.com/paper/2307.12502/) (2023)
- [Style Interleaved Learning for Generalizable Person Re-identification](https://mlsanity.com/paper/2207.03132/) (2022)
- [Normalization Perturbation: A Simple Domain Generalization Method for Real-World Domain Shifts](https://mlsanity.com/paper/2211.04393/) (2022)
- [Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach](https://mlsanity.com/paper/2302.12047/) (2023)
- [Domain Generalization with Adversarial Intensity Attack for Medical Image Segmentation](https://mlsanity.com/paper/2304.02720/) (2023)
- [Source-free Domain Adaptive Object Detection in Remote Sensing Images](https://mlsanity.com/paper/2401.17916/) (2024)
- [Domain Generalization with Small Data](https://mlsanity.com/paper/2402.06150/) (2024)
- [Domain Generalization for Crop Segmentation with Standardized Ensemble Knowledge Distillation](https://mlsanity.com/paper/2304.01029/) (2023)

## Abstract (arXiv)

Recent work has shown that convolutional neural network classifiers overly rely on texture at the expense of shape cues. We make a similar but different distinction between shape and local image cues, on the one hand, and global image statistics, on the other. Our method, called Permuted Adaptive Instance Normalization (pAdaIN), reduces the representation of global statistics in the hidden layers of image classifiers. pAdaIN samples a random permutation π that rearranges the samples in a given batch. Adaptive Instance Normalization (AdaIN) is then applied between the activations of each (non-permuted) sample i and the corresponding activations of the sample π(i), thus swapping statistics between the samples of the batch. Since the global image statistics are distorted, this swapping procedure causes the network to rely on cues, such as shape or texture. By choosing the random permutation with probability p and the identity permutation otherwise, one can control the effect's strength. With the correct choice of p, fixed apriori for all experiments and selected without considering test data, our method consistently outperforms baselines in multiple settings. In image classification, our method improves on both CIFAR100 and ImageNet using multiple architectures. In the setting of robustness, our method improves on both ImageNet-C and Cifar-100-C for multiple architectures. In the setting of domain adaptation and domain generalization, our method achieves state of the art results on the transfer learning task from GTAV to Cityscapes and on the PACS benchmark.