# Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training

arXiv: https://arxiv.org/abs/2202.07993 · HTML: https://mlsanity.com/paper/2202.07993/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 32 references that are in the map.
- First posted on arXiv 16 Feb 2022.

## Builds on (most cited first, 13 of 13)

- [A Simple Framework for Contrastive Learning of Visual Representations](https://mlsanity.com/paper/2002.05709/) (2020)
- [Momentum Contrast for Unsupervised Visual Representation Learning](https://mlsanity.com/paper/1911.05722/) (2019)
- [Bootstrap your own latent: A new approach to self-supervised Learning](https://mlsanity.com/paper/2006.07733/) (2020)
- [Exploring Simple Siamese Representation Learning](https://mlsanity.com/paper/2011.10566/) (2020)
- [Unsupervised Learning of Visual Features by Contrasting Cluster Assignments](https://mlsanity.com/paper/2006.09882/) (2020)
- [Improved Baselines with Momentum Contrastive Learning](https://mlsanity.com/paper/2003.04297/) (2020)
- [Barlow Twins: Self-Supervised Learning via Redundancy Reduction](https://mlsanity.com/paper/2103.03230/) (2021)
- [Unsupervised Visual Representation Learning by Context Prediction](https://mlsanity.com/paper/1505.05192/) (2015)
- [VICReg: Variance-Invariance-Covariance Regularization for Self-Supervised Learning](https://mlsanity.com/paper/2105.04906/) (2021)
- [What Makes for Good Views for Contrastive Learning?](https://mlsanity.com/paper/2005.10243/) (2020)
- [Discriminative Unsupervised Feature Learning with Exemplar Convolutional Neural Networks](https://mlsanity.com/paper/1406.6909/) (2014)
- [What Should Not Be Contrastive in Contrastive Learning](https://mlsanity.com/paper/2008.05659/) (2020)
- [Data-Driven Color Augmentation Techniques for Deep Skin Image Analysis](https://mlsanity.com/paper/1703.03702/) (2017)

## Built on by (most cited first, 10 of 10)

- [SignRep: Enhancing Self-Supervised Sign Representations](https://mlsanity.com/paper/2503.08529/) (2025)
- [Plasticity-Optimized Complementary Networks for Unsupervised Continual Learning](https://mlsanity.com/paper/2309.06086/) (2023)
- [Unifying Color and Lightness Correction with View-Adaptive Curve Adjustment for Robust 3D Novel View Synthesis](https://mlsanity.com/paper/2602.18322/) (2026)
- [Augmentation-aware Self-supervised Learning with Conditioned Projector](https://mlsanity.com/paper/2306.06082/) (2023)
- [Label Augmentation for Neural Networks Robustness](https://mlsanity.com/paper/2408.01977/) (2024)
- [LumiCtrl : Learning Illuminant Prompts for Lighting Control in Personalized Text-to-Image Models](https://mlsanity.com/paper/2512.17489/) (2025)
- [A Hypertoroidal Covering for Perfect Color Equivariance](https://mlsanity.com/paper/2603.04256/) (2026)
- [Multi-task Planar Reconstruction with Feature Warping Guidance](https://mlsanity.com/paper/2311.14981/) (2023)
- [Efficient Deep Learning Approaches for Processing Ultra-Widefield Retinal Imaging](https://mlsanity.com/paper/2503.18151/) (2025)
- [Maximizing Generalization: The Effect of Different Augmentation Techniques on Lightweight Vision Transformer for Bengali Character Classification](https://mlsanity.com/paper/2603.02591/) (2026)

## Abstract (arXiv)

Several recent works on self-supervised learning are trained by mapping different augmentations of the same image to the same feature representation. The data augmentations used are of crucial importance to the quality of learned feature representations. In this paper, we analyze how the color jitter traditionally used in data augmentation negatively impacts the quality of the color features in learned feature representations. To address this problem, we propose a more realistic, physics-based color data augmentation - which we call Planckian Jitter - that creates realistic variations in chromaticity and produces a model robust to illumination changes that can be commonly observed in real life, while maintaining the ability to discriminate image content based on color information. Experiments confirm that such a representation is complementary to the representations learned with the currently-used color jitter augmentation and that a simple concatenation leads to significant performance gains on a wide range of downstream datasets. In addition, we present a color sensitivity analysis that documents the impact of different training methods on model neurons and shows that the performance of the learned features is robust with respect to illuminant variations.