Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement
Abstract In order to solve the problem of weak single domain generalization ability in existing crowd counting methods, this study proposes a new crowd counting framework called Multi-scale Attention and Hierarchy level Enhancement (MAHE). Firstly, the model can focus on both the detailed features a...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-01-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-024-83725-5 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841559587140927488 |
|---|---|
| author | Jiarui Zhou Jianming Zhang Yan Gui |
| author_facet | Jiarui Zhou Jianming Zhang Yan Gui |
| author_sort | Jiarui Zhou |
| collection | DOAJ |
| description | Abstract In order to solve the problem of weak single domain generalization ability in existing crowd counting methods, this study proposes a new crowd counting framework called Multi-scale Attention and Hierarchy level Enhancement (MAHE). Firstly, the model can focus on both the detailed features and the macro information of structural position changes through the fusion of channel attention and spatial attention. Secondly, the addition of multi-head attention feature module facilitates the model’s capacity to effectively capture complex dependency relationships between sequence elements. In addition, the three-stage encoding and decoding processing mode enables the model to effectively represent crowd density information. Finally, the fusion of multi-scale features derived from different receptive fields is further enhanced through multi-scale hierarchy level feature fusion, thereby enabling the model to learn high-level semantic information and low-level multi-scale visual field feature information. This method enhances the model’s capacity to capture key feature information, even in highly differentiated datasets, thereby improving the model’s generalization ability on a single domain. The model has demonstrated strong generalization capabilities through extensive experiments on different datasets. This study not only improves the accuracy of crowd counting, but also introduces a new research approach for single domain generalization of crowd counting. |
| format | Article |
| id | doaj-art-282d22b3694c47239ef3787aa30d71c1 |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-282d22b3694c47239ef3787aa30d71c12025-01-05T12:21:28ZengNature PortfolioScientific Reports2045-23222025-01-0115111410.1038/s41598-024-83725-5Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancementJiarui Zhou0Jianming Zhang1Yan Gui2School of Computer and Communication Engineering, Changsha University of Science and TechnologySchool of Computer and Communication Engineering, Changsha University of Science and TechnologySchool of Computer and Communication Engineering, Changsha University of Science and TechnologyAbstract In order to solve the problem of weak single domain generalization ability in existing crowd counting methods, this study proposes a new crowd counting framework called Multi-scale Attention and Hierarchy level Enhancement (MAHE). Firstly, the model can focus on both the detailed features and the macro information of structural position changes through the fusion of channel attention and spatial attention. Secondly, the addition of multi-head attention feature module facilitates the model’s capacity to effectively capture complex dependency relationships between sequence elements. In addition, the three-stage encoding and decoding processing mode enables the model to effectively represent crowd density information. Finally, the fusion of multi-scale features derived from different receptive fields is further enhanced through multi-scale hierarchy level feature fusion, thereby enabling the model to learn high-level semantic information and low-level multi-scale visual field feature information. This method enhances the model’s capacity to capture key feature information, even in highly differentiated datasets, thereby improving the model’s generalization ability on a single domain. The model has demonstrated strong generalization capabilities through extensive experiments on different datasets. This study not only improves the accuracy of crowd counting, but also introduces a new research approach for single domain generalization of crowd counting.https://doi.org/10.1038/s41598-024-83725-5Crowd countingSpatial attentionChannel attentionMulti-scale featuresDomain generalization |
| spellingShingle | Jiarui Zhou Jianming Zhang Yan Gui Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement Scientific Reports Crowd counting Spatial attention Channel attention Multi-scale features Domain generalization |
| title | Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement |
| title_full | Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement |
| title_fullStr | Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement |
| title_full_unstemmed | Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement |
| title_short | Crowd counting in domain generalization based on multi-scale attention and hierarchy level enhancement |
| title_sort | crowd counting in domain generalization based on multi scale attention and hierarchy level enhancement |
| topic | Crowd counting Spatial attention Channel attention Multi-scale features Domain generalization |
| url | https://doi.org/10.1038/s41598-024-83725-5 |
| work_keys_str_mv | AT jiaruizhou crowdcountingindomaingeneralizationbasedonmultiscaleattentionandhierarchylevelenhancement AT jianmingzhang crowdcountingindomaingeneralizationbasedonmultiscaleattentionandhierarchylevelenhancement AT yangui crowdcountingindomaingeneralizationbasedonmultiscaleattentionandhierarchylevelenhancement |