RCCFormer: A Robust Crowd Counting Network Based on Transformer

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Liu, Peng, Li, Heng-Chao, Lei, Sen, Liu, Nanqing, Feng, Bin, Wu, Xiao
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866912313196412928
author Liu, Peng
Li, Heng-Chao
Lei, Sen
Liu, Nanqing
Feng, Bin
Wu, Xiao
author_facet Liu, Peng
Li, Heng-Chao
Lei, Sen
Liu, Nanqing
Feng, Bin
Wu, Xiao
contents Crowd counting, which is a key computer vision task, has emerged as a fundamental technology in crowd analysis and public safety management. However, challenges such as scale variations and complex backgrounds significantly impact the accuracy of crowd counting. To mitigate these issues, this paper proposes a robust Transformer-based crowd counting network, termed RCCFormer, specifically designed for background suppression and scale awareness. The proposed method incorporates a Multi-level Feature Fusion Module (MFFM), which meticulously integrates features extracted at diverse stages of the backbone architecture. It establishes a strong baseline capable of capturing intricate and comprehensive feature representations, surpassing traditional baselines. Furthermore, the introduced Detail-Embedded Attention Block (DEAB) captures contextual information and local details through global self-attention and local attention along with a learnable manner for efficient fusion. This enhances the model's ability to focus on foreground regions while effectively mitigating background noise interference. Additionally, we develop an Adaptive Scale-Aware Module (ASAM), with our novel Input-dependent Deformable Convolution (IDConv) as its fundamental building block. This module dynamically adapts to changes in head target shapes and scales, significantly improving the network's capability to accommodate large-scale variations. The effectiveness of the proposed method is validated on the ShanghaiTech Part_A and Part_B, NWPU-Crowd, and QNRF datasets. The results demonstrate that our RCCFormer achieves excellent performance across all four datasets, showcasing state-of-the-art outcomes.
format Preprint
id arxiv_https___arxiv_org_abs_2504_04935
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle RCCFormer: A Robust Crowd Counting Network Based on Transformer
Liu, Peng
Li, Heng-Chao
Lei, Sen
Liu, Nanqing
Feng, Bin
Wu, Xiao
Computer Vision and Pattern Recognition
Artificial Intelligence
Crowd counting, which is a key computer vision task, has emerged as a fundamental technology in crowd analysis and public safety management. However, challenges such as scale variations and complex backgrounds significantly impact the accuracy of crowd counting. To mitigate these issues, this paper proposes a robust Transformer-based crowd counting network, termed RCCFormer, specifically designed for background suppression and scale awareness. The proposed method incorporates a Multi-level Feature Fusion Module (MFFM), which meticulously integrates features extracted at diverse stages of the backbone architecture. It establishes a strong baseline capable of capturing intricate and comprehensive feature representations, surpassing traditional baselines. Furthermore, the introduced Detail-Embedded Attention Block (DEAB) captures contextual information and local details through global self-attention and local attention along with a learnable manner for efficient fusion. This enhances the model's ability to focus on foreground regions while effectively mitigating background noise interference. Additionally, we develop an Adaptive Scale-Aware Module (ASAM), with our novel Input-dependent Deformable Convolution (IDConv) as its fundamental building block. This module dynamically adapts to changes in head target shapes and scales, significantly improving the network's capability to accommodate large-scale variations. The effectiveness of the proposed method is validated on the ShanghaiTech Part_A and Part_B, NWPU-Crowd, and QNRF datasets. The results demonstrate that our RCCFormer achieves excellent performance across all four datasets, showcasing state-of-the-art outcomes.
title RCCFormer: A Robust Crowd Counting Network Based on Transformer
topic Computer Vision and Pattern Recognition
Artificial Intelligence
url https://arxiv.org/abs/2504.04935