# Inverse Attention Guided Deep Crowd Counting Network

## TL;DR

This paper introduces IA-DCCN, a crowd counting network that uses inverse attention guided by segmentation to improve accuracy in congested scenes with minimal extra computation.

## Contribution

It presents a novel inverse attention mechanism that incorporates segmentation info into a deep crowd counting network, enhancing performance without extra annotations.

## Key findings

- Achieves significant accuracy improvements on three challenging datasets.
- Incorporates segmentation information with minimal computational overhead.
- Demonstrates effectiveness through ablation studies and detailed analysis.

## Abstract

In this paper, we address the challenging problem of crowd counting in congested scenes. Specifically, we present Inverse Attention Guided Deep Crowd Counting Network (IA-DCCN) that efficiently infuses segmentation information through an inverse attention mechanism into the counting network, resulting in significant improvements. The proposed method, which is based on VGG-16, is a single-step training framework and is simple to implement. The use of segmentation information results in minimal computational overhead and does not require any additional annotations. We demonstrate the significance of segmentation guided inverse attention through a detailed analysis and ablation study. Furthermore, the proposed method is evaluated on three challenging crowd counting datasets and is shown to achieve significant improvements over several recent methods.