# Rethinking Image Histogram Matching for Image Classification

arXiv: https://arxiv.org/abs/2506.01346 · HTML: https://mlsanity.com/paper/2506.01346/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 27 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 15 of 15)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Zero-Reference Deep Curve Estimation for Low-Light Image Enhancement](https://mlsanity.com/paper/2001.06826/) (2020)
- [Learning to Enhance Low-Light Image via Zero-Reference Deep Curve Estimation](https://mlsanity.com/paper/2103.00860/) (2021)
- [Learning Image-adaptive 3D Lookup Tables for High Performance Photo Enhancement in Real-time](https://mlsanity.com/paper/2009.14468/) (2020)
- [Restoring Images in Adverse Weather Conditions via Histogram Transformer](https://mlsanity.com/paper/2407.10172/) (2024)
- [Learning Deep Embeddings with Histogram Loss](https://mlsanity.com/paper/1611.00822/) (2016)
- [Zero-Shot Day-Night Domain Adaptation with a Physics Prior](https://mlsanity.com/paper/2108.05137/) (2021)
- [DAWN: Vehicle Detection in Adverse Weather Nature Dataset](https://mlsanity.com/paper/2008.05402/) (2020)
- [Raw or Cooked? Object Detection on RAW Images](https://mlsanity.com/paper/2301.08965/) (2023)
- [Similarity Min-Max: Zero-Shot Day-Night Domain Adaptation](https://mlsanity.com/paper/2307.08779/) (2023)
- [Learnable Histogram: Statistical Context Features for Deep Neural Networks](https://mlsanity.com/paper/1804.09398/) (2018)
- [ERUP-YOLO: Enhancing Object Detection Robustness for Adverse Weather Condition by Unified Image-Adaptive Processing](https://mlsanity.com/paper/2411.02799/) (2024)
- [Differentiable Histogram with Hard-Binning](https://mlsanity.com/paper/2012.06311/) (2020)
- [Self-Aligned Concave Curve: Illumination Enhancement for Unsupervised Adaptation](https://mlsanity.com/paper/2210.03792/) (2022)
- [Improving Low-Light Image Recognition Performance Based on Image-adaptive Learnable Module](https://mlsanity.com/paper/2401.06438/) (2024)

## Built on by (most cited first, 2 of 2)

- [IA-CLAHE: Image-Adaptive Clip Limit Estimation for CLAHE](https://mlsanity.com/paper/2604.16010/) (2026)
- [Evaluating Histogram Matching for Robust Deep learning-Based Grapevine Disease Detection](https://mlsanity.com/paper/2604.19510/) (2026)

## Abstract (arXiv)

This paper rethinks image histogram matching (HM) and proposes a differentiable and parametric HM preprocessing for a downstream classifier. Convolutional neural networks have demonstrated remarkable achievements in classification tasks. However, they often exhibit degraded performance on low-contrast images captured under adverse weather conditions. To maintain classifier performance under low-contrast images, histogram equalization (HE) is commonly used. HE is a special case of HM using a uniform distribution as a target pixel value distribution. In this paper, we focus on the shape of the target pixel value distribution. Compared to a uniform distribution, a single, well-designed distribution could have potential to improve the performance of the downstream classifier across various adverse weather conditions. Based on this hypothesis, we propose a differentiable and parametric HM that optimizes the target distribution using the loss function of the downstream classifier. This method addresses pixel value imbalances by transforming input images with arbitrary distributions into a target distribution optimized for the classifier. Our HM is trained on only normal weather images using the classifier. Experimental results show that a classifier trained with our proposed HM outperforms conventional preprocessing methods under adverse weather conditions.