# Universal Background Subtraction based on Arithmetic Distribution Neural Network

arXiv: https://arxiv.org/abs/2104.08390 · HTML: https://mlsanity.com/paper/2104.08390/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 99 references that are in the map.
- First posted on arXiv 16 Apr 2021.

## Builds on (most cited first, 14 of 14)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Background Subtraction in Real Applications: Challenges, Current Models and Future Directions](https://mlsanity.com/paper/1901.03577/) (2019)
- [Learning Multi-scale Features for Foreground Segmentation](https://mlsanity.com/paper/1808.01477/) (2018)
- [Deep Neural Network Concepts for Background Subtraction: A Systematic Review and Comparative Evaluation](https://mlsanity.com/paper/1811.05255/) (2018)
- [Robust Subspace Learning: Robust PCA, Robust Subspace Tracking, and Robust Subspace Recovery](https://mlsanity.com/paper/1711.09492/) (2017)
- [BSUV-Net: A Fully-Convolutional Neural Network for Background Subtraction of Unseen Videos](https://mlsanity.com/paper/1907.11371/) (2019)
- [BSUV-Net 2.0: Spatio-Temporal Data Augmentations for Video-Agnostic Supervised Background Subtraction](https://mlsanity.com/paper/2101.09585/) (2021)
- [Towards Benchmarking Scene Background Initialization](https://mlsanity.com/paper/1506.04051/) (2015)
- [Robust PCA via Nonconvex Rank Approximation](https://mlsanity.com/paper/1511.05261/) (2015)
- [Robust Online Matrix Factorization for Dynamic Background Subtraction](https://mlsanity.com/paper/1705.10000/) (2017)
- [Combining Background Subtraction Algorithms with Convolutional Neural Network](https://mlsanity.com/paper/1807.02080/) (2018)
- [How Far Can You Get By Combining Change Detection Algorithms?](https://mlsanity.com/paper/1505.02921/) (2015)

## Built on by (most cited first, 11 of 11)

- [ZBS: Zero-shot Background Subtraction via Instance-level Background Modeling and Foreground Selection](https://mlsanity.com/paper/2303.14679/) (2023)
- [Instance-Level Moving Object Segmentation from a Single Image with Events](https://mlsanity.com/paper/2502.12975/) (2025)
- [LangGas: Introducing Language in Selective Zero-Shot Background Subtraction for Semi-Transparent Gas Leak Detection with a New Dataset](https://mlsanity.com/paper/2503.02910/) (2025)
- [Learning Temporal Distribution and Spatial Correlation Towards Universal Moving Object Segmentation](https://mlsanity.com/paper/2304.09949/) (2023)
- [Learning Spatial-Temporal Regularized Tensor Sparse RPCA for Background Subtraction](https://mlsanity.com/paper/2309.15576/) (2023)
- [Bridging Distribution Learning and Image Clustering in High-dimensional Space](https://mlsanity.com/paper/2308.15667/) (2023)
- [Beyond Motion Cues and Structural Sparsity: Revisiting Small Moving Target Detection](https://mlsanity.com/paper/2509.07654/) (2025)
- [Lightweight Monocular Depth Estimation](https://mlsanity.com/paper/2212.11363/) (2022)
- [MM811 Project Report: Cloud Detection and Removal in Satellite Images](https://mlsanity.com/paper/2212.11369/) (2022)
- [Application Of ADNN For Background Subtraction In Smart Surveillance System](https://mlsanity.com/paper/2301.00264/) (2022)
- [Deep Clustering via Distribution Learning](https://mlsanity.com/paper/2408.03407/) (2024)

## Abstract (arXiv)

We propose a universal background subtraction framework based on the Arithmetic Distribution Neural Network (ADNN) for learning the distributions of temporal pixels. In our ADNN model, the arithmetic distribution operations are utilized to introduce the arithmetic distribution layers, including the product distribution layer and the sum distribution layer. Furthermore, in order to improve the accuracy of the proposed approach, an improved Bayesian refinement model based on neighboring information, with a GPU implementation, is incorporated. In the forward pass and backpropagation of the proposed arithmetic distribution layers, histograms are considered as probability density functions rather than matrices. Thus, the proposed approach is able to utilize the probability information of the histogram and achieve promising results with a very simple architecture compared to traditional convolutional neural networks. Evaluations using standard benchmarks demonstrate the superiority of the proposed approach compared to state-of-the-art traditional and deep learning methods. To the best of our knowledge, this is the first method to propose network layers based on arithmetic distribution operations for learning distributions during background subtraction.