# What Else Can Fool Deep Learning? Addressing Color Constancy Errors on Deep Neural Network Performance

arXiv: https://arxiv.org/abs/1912.06960 · HTML: https://mlsanity.com/paper/1912.06960/

## Key facts

- Cited by 37 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2019.

## Built on by (most cited first, 30 of 37)

- [A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?](https://mlsanity.com/paper/2112.00639/) (2021)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [Grounding Visual Illusions in Language: Do Vision-Language Models Perceive Illusions Like Humans?](https://mlsanity.com/paper/2311.00047/) (2023)
- [IllusionVQA: A Challenging Optical Illusion Dataset for Vision Language Models](https://mlsanity.com/paper/2403.15952/) (2024)
- [ILIAS: Instance-Level Image retrieval At Scale](https://mlsanity.com/paper/2502.11748/) (2025)
- [CLCC: Contrastive Learning for Color Constancy](https://mlsanity.com/paper/2106.04989/) (2021)
- [Balancing Logit Variation for Long-tailed Semantic Segmentation](https://mlsanity.com/paper/2306.02061/) (2023)
- [Auto White-Balance Correction for Mixed-Illuminant Scenes](https://mlsanity.com/paper/2109.08750/) (2021)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images](https://mlsanity.com/paper/2408.14802/) (2024)
- [Efficient Visual Computing with Camera RAW Snapshots](https://mlsanity.com/paper/2212.07778/) (2022)
- [Ethical Considerations for Responsible Data Curation](https://mlsanity.com/paper/2302.03629/) (2023)
- [Deepfake Forensics via An Adversarial Game](https://mlsanity.com/paper/2103.13567/) (2021)
- [Beyond the Pixel: a Photometrically Calibrated HDR Dataset for Luminance and Color Prediction](https://mlsanity.com/paper/2304.12372/) (2023)
- [TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers](https://mlsanity.com/paper/2105.03906/) (2021)
- [Learning Enriched Illuminants for Cross and Single Sensor Color Constancy](https://mlsanity.com/paper/2203.11068/) (2022)
- [Exploring Resolution and Degradation Clues as Self-supervised Signal for Low Quality Object Detection](https://mlsanity.com/paper/2208.03062/) (2022)
- [Evaluating Vision-Language Models on Bistable Images](https://mlsanity.com/paper/2405.19423/) (2024)
- [ColorSense: A Study on Color Vision in Machine Visual Recognition](https://mlsanity.com/paper/2212.08650/) (2022)
- [Analysis of Classifier Training on Synthetic Data for Cross-Domain Datasets](https://mlsanity.com/paper/2410.22748/) (2024)
- [Multi-color balance for color constancy](https://mlsanity.com/paper/2105.10228/) (2021)
- [Probing the Effect of Selection Bias on Generalization: A Thought Experiment](https://mlsanity.com/paper/2105.09934/) (2021)
- [Interactive Portrait Harmonization](https://mlsanity.com/paper/2203.08216/) (2022)
- [NeuSurfEmb: A Complete Pipeline for Dense Correspondence-based 6D Object Pose Estimation without CAD Models](https://mlsanity.com/paper/2407.12207/) (2024)
- [Leveraging Content and Context Cues for Low-Light Image Enhancement](https://mlsanity.com/paper/2412.07693/) (2024)
- [RAW-Adapter: Adapting Pre-trained Visual Model to Camera RAW Images and A Benchmark](https://mlsanity.com/paper/2503.17027/) (2025)
- [Spatially varying white balancing for mixed and non-uniform illuminants](https://mlsanity.com/paper/2109.01350/) (2021)
- [Advancing Perception in Artificial Intelligence through Principles of Cognitive Science](https://mlsanity.com/paper/2310.08803/) (2023)
- [Multi-illuminant Color Constancy via Multi-scale Illuminant Estimation and Fusion](https://mlsanity.com/paper/2502.02021/) (2025)
- [Defending Against Frequency-Based Attacks with Diffusion Models](https://mlsanity.com/paper/2504.11034/) (2025)
- [RestoreDet: Degradation Equivariant Representation for Object Detection in Low Resolution Images](https://mlsanity.com/paper/2201.02314/) (2022)

## Abstract (arXiv)

There is active research targeting local image manipulations that can fool deep neural networks (DNNs) into producing incorrect results. This paper examines a type of global image manipulation that can produce similar adverse effects. Specifically, we explore how strong color casts caused by incorrectly applied computational color constancy - referred to as white balance (WB) in photography - negatively impact the performance of DNNs targeting image segmentation and classification. In addition, we discuss how existing image augmentation methods used to improve the robustness of DNNs are not well suited for modeling WB errors. To address this problem, a novel augmentation method is proposed that can emulate accurate color constancy degradation. We also explore pre-processing training and testing images with a recent WB correction algorithm to reduce the effects of incorrectly white-balanced images. We examine both augmentation and pre-processing strategies on different datasets and demonstrate notable improvements on the CIFAR-10, CIFAR-100, and ADE20K datasets.