Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | https://arxiv.org/abs/2404.07847 |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866918144383123456 |
|---|---|
| author | Chen, Lei Gao, Xinghang Chao, Fei Chang, Xiang Lin, Chih Min Gao, Xingen Lin, Shaopeng Zhang, Hongyi Lin, Juqiang |
| author_facet | Chen, Lei Gao, Xinghang Chao, Fei Chang, Xiang Lin, Chih Min Gao, Xingen Lin, Shaopeng Zhang, Hongyi Lin, Juqiang |
| contents | In the field of crowd counting research, many recent deep learning based methods have demonstrated robust capabilities for accurately estimating crowd sizes. However, the enhancement in their performance often arises from an increase in the complexity of the model structure. This paper discusses how to construct high-performance crowd counting models using only simple structures. We proposes the Fuss-Free Network (FFNet) that is characterized by its simple and efficieny structure, consisting of only a backbone network and a multi-scale feature fusion structure. The multi-scale feature fusion structure is a simple structure consisting of three branches, each only equipped with a focus transition module, and combines the features from these branches through the concatenation operation. Our proposed crowd counting model is trained and evaluated on four widely used public datasets, and it achieves accuracy that is comparable to that of existing complex models. Furthermore, we conduct a comprehensive evaluation by replacing the existing backbones of various models such as FFNet and CCTrans with different networks, including MobileNet-v3, ConvNeXt-Tiny, and Swin-Transformer-Small. The experimental results further indicate that excellent crowd counting performance can be achieved with the simplied structure proposed by us. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_07847 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | The Effectiveness of a Simplified Model Structure for Crowd Counting Chen, Lei Gao, Xinghang Chao, Fei Chang, Xiang Lin, Chih Min Gao, Xingen Lin, Shaopeng Zhang, Hongyi Lin, Juqiang Computer Vision and Pattern Recognition In the field of crowd counting research, many recent deep learning based methods have demonstrated robust capabilities for accurately estimating crowd sizes. However, the enhancement in their performance often arises from an increase in the complexity of the model structure. This paper discusses how to construct high-performance crowd counting models using only simple structures. We proposes the Fuss-Free Network (FFNet) that is characterized by its simple and efficieny structure, consisting of only a backbone network and a multi-scale feature fusion structure. The multi-scale feature fusion structure is a simple structure consisting of three branches, each only equipped with a focus transition module, and combines the features from these branches through the concatenation operation. Our proposed crowd counting model is trained and evaluated on four widely used public datasets, and it achieves accuracy that is comparable to that of existing complex models. Furthermore, we conduct a comprehensive evaluation by replacing the existing backbones of various models such as FFNet and CCTrans with different networks, including MobileNet-v3, ConvNeXt-Tiny, and Swin-Transformer-Small. The experimental results further indicate that excellent crowd counting performance can be achieved with the simplied structure proposed by us. |
| title | The Effectiveness of a Simplified Model Structure for Crowd Counting |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.07847 |