# Differentiable Histogram with Hard-Binning

arXiv: https://arxiv.org/abs/2012.06311 · HTML: https://mlsanity.com/paper/2012.06311/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Nov 2020.

## Built on by (most cited first, 5 of 5)

- [Quantification using Permutation-Invariant Networks based on Histograms](https://mlsanity.com/paper/2403.15123/) (2024)
- [Self-Supervised Face Image Restoration with a One-Shot Reference](https://mlsanity.com/paper/2203.03005/) (2022)
- [Histogram Layers for Synthetic Aperture Sonar Imagery](https://mlsanity.com/paper/2209.03878/) (2022)
- [Rethinking Image Histogram Matching for Image Classification](https://mlsanity.com/paper/2506.01346/) (2025)
- [Smudged Fingerprints: A Systematic Evaluation of the Robustness of AI Image Fingerprints](https://mlsanity.com/paper/2512.11771/) (2025)

## Abstract (arXiv)

The simplicity and expressiveness of a histogram render it a useful feature in different contexts including deep learning. Although the process of computing a histogram is non-differentiable, researchers have proposed differentiable approximations, which have some limitations. A differentiable histogram that directly approximates the hard-binning operation in conventional histograms is proposed. It combines the strength of existing differentiable histograms and overcomes their individual challenges. In comparison to a histogram computed using Numpy, the proposed histogram has an absolute approximation error of 0.000158.