# Bound Tightening Network for Robust Crowd Counting

arXiv: https://arxiv.org/abs/2409.19146 · HTML: https://mlsanity.com/paper/2409.19146/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 17 references that are in the map.
- First posted on arXiv 27 Sep 2024.

## Builds on (most cited first, 8 of 8)

- [On the Effectiveness of Interval Bound Propagation for Training Verifiably Robust Models](https://mlsanity.com/paper/1810.12715/) (2018)
- [Towards Stable and Efficient Training of Verifiably Robust Neural Networks](https://mlsanity.com/paper/1906.06316/) (2019)
- [Bayesian Loss for Crowd Count Estimation with Point Supervision](https://mlsanity.com/paper/1908.03684/) (2019)
- [Harnessing Perceptual Adversarial Patches for Crowd Counting](https://mlsanity.com/paper/2109.07986/) (2021)
- [Learning Spatial Awareness to Improve Crowd Counting](https://mlsanity.com/paper/1909.07057/) (2019)
- [Multi-scale Convolutional Neural Networks for Crowd Counting](https://mlsanity.com/paper/1702.02359/) (2017)
- [Towards Adversarial Patch Analysis and Certified Defense against Crowd Counting](https://mlsanity.com/paper/2104.10868/) (2021)
- [A-CCNN: adaptive ccnn for density estimation and crowd counting](https://mlsanity.com/paper/1804.06958/) (2018)

## Abstract (arXiv)

Crowd Counting is a fundamental topic, aiming to estimate the number of individuals in the crowded images or videos fed from surveillance cameras. Recent works focus on improving counting accuracy, while ignoring the certified robustness of counting models. In this paper, we propose a novel Bound Tightening Network (BTN) for Robust Crowd Counting. It consists of three parts: base model, smooth regularization module and certify bound module. The core idea is to propagate the interval bound through the base model (certify bound module) and utilize the layer weights (smooth regularization module) to guide the network learning. Experiments on different benchmark datasets for counting demonstrate the effectiveness and efficiency of BTN.