# Interlayer and Intralayer Scale Aggregation for Scale-invariant Crowd Counting

arXiv: https://arxiv.org/abs/2005.11943 · HTML: https://mlsanity.com/paper/2005.11943/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 May 2020.

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

- [Mutually-Aware Feature Learning for Few-Shot Object Counting](https://mlsanity.com/paper/2408.09734/) (2024)
- [Reducing Capacity Gap in Knowledge Distillation with Review Mechanism for Crowd Counting](https://mlsanity.com/paper/2206.05475/) (2022)

## Abstract (arXiv)

Crowd counting is an important vision task, which faces challenges on continuous scale variation within a given scene and huge density shift both within and across images. These challenges are typically addressed using multi-column structures in existing methods. However, such an approach does not provide consistent improvement and transferability due to limited ability in capturing multi-scale features, sensitiveness to large density shift, and difficulty in training multi-branch models. To overcome these limitations, a Single-column Scale-invariant Network (ScSiNet) is presented in this paper, which extracts sophisticated scale-invariant features via the combination of interlayer multi-scale integration and a novel intralayer scale-invariant transformation (SiT). Furthermore, in order to enlarge the diversity of densities, a randomly integrated loss is presented for training our single-branch method. Extensive experiments on public datasets demonstrate that the proposed method consistently outperforms state-of-the-art approaches in counting accuracy and achieves remarkable transferability and scale-invariant property.