# Whitening and Coloring batch transform for GANs

arXiv: https://arxiv.org/abs/1806.00420 · HTML: https://mlsanity.com/paper/1806.00420/

## Key facts

- Cited by 27 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Jun 2018.

## Built on by (most cited first, 27 of 27)

- [RobustNet: Improving Domain Generalization in Urban-Scene Segmentation via Instance Selective Whitening](https://mlsanity.com/paper/2103.15597/) (2021)
- [On Feature Decorrelation in Self-Supervised Learning](https://mlsanity.com/paper/2105.00470/) (2021)
- [Rebooting ACGAN: Auxiliary Classifier GANs with Stable Training](https://mlsanity.com/paper/2111.01118/) (2021)
- [ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond](https://mlsanity.com/paper/2303.06562/) (2023)
- [StudioGAN: A Taxonomy and Benchmark of GANs for Image Synthesis](https://mlsanity.com/paper/2206.09479/) (2022)
- [An Investigation into Whitening Loss for Self-supervised Learning](https://mlsanity.com/paper/2210.03586/) (2022)
- [Robust Differentiable SVD](https://mlsanity.com/paper/2104.03821/) (2021)
- [VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution](https://mlsanity.com/paper/2304.01434/) (2023)
- [Fast Differentiable Matrix Square Root and Inverse Square Root](https://mlsanity.com/paper/2201.12543/) (2022)
- [Fast Differentiable Matrix Square Root](https://mlsanity.com/paper/2201.08663/) (2022)
- [More Synergy, Less Redundancy: Exploiting Joint Mutual Information for Self-Supervised Learning](https://mlsanity.com/paper/2307.00651/) (2023)
- [Modulate Your Spectrum in Self-Supervised Learning](https://mlsanity.com/paper/2305.16789/) (2023)
- [Details Matter for Indoor Open-vocabulary 3D Instance Segmentation](https://mlsanity.com/paper/2507.23134/) (2025)
- [Orthogonal SVD Covariance Conditioning and Latent Disentanglement](https://mlsanity.com/paper/2212.05599/) (2022)
- [Hierarchical Semantic Tree Concept Whitening for Interpretable Image Classification](https://mlsanity.com/paper/2307.04343/) (2023)
- [Computer Vision Self-supervised Learning Methods on Time Series](https://mlsanity.com/paper/2109.00783/) (2021)
- [Improving Covariance Conditioning of the SVD Meta-layer by Orthogonality](https://mlsanity.com/paper/2207.02119/) (2022)
- [Improving Generalization of Batch Whitening by Convolutional Unit Optimization](https://mlsanity.com/paper/2108.10629/) (2021)
- [Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models](https://mlsanity.com/paper/2112.03860/) (2021)
- [Neural Multivariate Regression: Qualitative Insights from the Unconstrained Feature Model](https://mlsanity.com/paper/2505.09308/) (2025)
- [Controllable Feature Whitening for Hyperparameter-Free Bias Mitigation](https://mlsanity.com/paper/2507.20284/) (2025)
- [Towards Controllable and Photorealistic Region-wise Image Manipulation](https://mlsanity.com/paper/2108.08674/) (2021)
- [Whitening Not Recommended for Classification Tasks in LLMs](https://mlsanity.com/paper/2407.12886/) (2024)
- [Covariance-corrected Whitening Alleviates Network Degeneration on Imbalanced Classification](https://mlsanity.com/paper/2408.17197/) (2024)
- [IBNorm: Information-Bottleneck Inspired Normalization for Representation Learning](https://mlsanity.com/paper/2510.25262/) (2025)
- [You Only Need End-to-End Training for Long-Tailed Recognition](https://mlsanity.com/paper/2112.05958/) (2021)
- [Direct Coloring for Self-Supervised Enhanced Feature Decoupling](https://mlsanity.com/paper/2412.02109/) (2024)

## Abstract (arXiv)

Batch Normalization (BN) is a common technique used to speed-up and stabilize training. On the other hand, the learnable parameters of BN are commonly used in conditional Generative Adversarial Networks (cGANs) for representing class-specific information using conditional Batch Normalization (cBN). In this paper we propose to generalize both BN and cBN using a Whitening and Coloring based batch normalization. We show that our conditional Coloring can represent categorical conditioning information which largely helps the cGAN qualitative results. Moreover, we show that full-feature whitening is important in a general GAN scenario in which the training process is known to be highly unstable. We test our approach on different datasets and using different GAN networks and training protocols, showing a consistent improvement in all the tested frameworks. Our CIFAR-10 conditioned results are higher than all previous works on this dataset.