Refined feature enhancement network for object detection
Abstract Convolutional neural networks-based object detection techniques have achieved positive performances. However, due to the limitations of local receptive field, some existing object detection methods cannot effectively capture global information in feature extraction phases, and thus lead to...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Springer
2024-11-01
|
| Series: | Complex & Intelligent Systems |
| Subjects: | |
| Online Access: | https://doi.org/10.1007/s40747-024-01622-w |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571176499544064 |
|---|---|
| author | Zonghui Li Yongsheng Dong |
| author_facet | Zonghui Li Yongsheng Dong |
| author_sort | Zonghui Li |
| collection | DOAJ |
| description | Abstract Convolutional neural networks-based object detection techniques have achieved positive performances. However, due to the limitations of local receptive field, some existing object detection methods cannot effectively capture global information in feature extraction phases, and thus lead to unsatisfactory detection performance. Moreover, the feature information extracted by the backbone network may be redundant. To alleviate these problems, in this paper we propose a refined feature enhancement network (RFENet) for object detection. Specifically, we first propose a feature enhancement module (FEM) to capture more global and local information from feature maps with certain long-range dependencies. We further propose a multi-branch dilated attention mechanism (MDAM) to refine the extracted features in a weighted form, which can select more important spatial and channel information and broaden the receptive field of the network. Finally, we validate RFENet on MS-COCO2017, PASCAL VOC2012, and PASCAL VOC07+12 datasets, respectively. Compared to the baseline network, our RFENet improves by 2.4 AP on MS-COCO2017 dataset, 3.4 mAP on PASCAL VOC2012 dataset, and 2.7 mAP on PASCAL VOC07+12 dataset. Extensive experiments show that our RFENet can perform competitively on different datasets. The code is available at https://github.com/object9detection/RFENet . |
| format | Article |
| id | doaj-art-7df70e54e3884e089c6bea4b7bbeca59 |
| institution | Kabale University |
| issn | 2199-4536 2198-6053 |
| language | English |
| publishDate | 2024-11-01 |
| publisher | Springer |
| record_format | Article |
| series | Complex & Intelligent Systems |
| spelling | doaj-art-7df70e54e3884e089c6bea4b7bbeca592025-02-02T12:48:56ZengSpringerComplex & Intelligent Systems2199-45362198-60532024-11-0111111510.1007/s40747-024-01622-wRefined feature enhancement network for object detectionZonghui Li0Yongsheng Dong1School of Information Engineering, Henan University of Science and TechnologySchool of Information Engineering, Henan University of Science and TechnologyAbstract Convolutional neural networks-based object detection techniques have achieved positive performances. However, due to the limitations of local receptive field, some existing object detection methods cannot effectively capture global information in feature extraction phases, and thus lead to unsatisfactory detection performance. Moreover, the feature information extracted by the backbone network may be redundant. To alleviate these problems, in this paper we propose a refined feature enhancement network (RFENet) for object detection. Specifically, we first propose a feature enhancement module (FEM) to capture more global and local information from feature maps with certain long-range dependencies. We further propose a multi-branch dilated attention mechanism (MDAM) to refine the extracted features in a weighted form, which can select more important spatial and channel information and broaden the receptive field of the network. Finally, we validate RFENet on MS-COCO2017, PASCAL VOC2012, and PASCAL VOC07+12 datasets, respectively. Compared to the baseline network, our RFENet improves by 2.4 AP on MS-COCO2017 dataset, 3.4 mAP on PASCAL VOC2012 dataset, and 2.7 mAP on PASCAL VOC07+12 dataset. Extensive experiments show that our RFENet can perform competitively on different datasets. The code is available at https://github.com/object9detection/RFENet .https://doi.org/10.1007/s40747-024-01622-wConvolutional neural networksObject detectionGlobal informationLong-range dependencies |
| spellingShingle | Zonghui Li Yongsheng Dong Refined feature enhancement network for object detection Complex & Intelligent Systems Convolutional neural networks Object detection Global information Long-range dependencies |
| title | Refined feature enhancement network for object detection |
| title_full | Refined feature enhancement network for object detection |
| title_fullStr | Refined feature enhancement network for object detection |
| title_full_unstemmed | Refined feature enhancement network for object detection |
| title_short | Refined feature enhancement network for object detection |
| title_sort | refined feature enhancement network for object detection |
| topic | Convolutional neural networks Object detection Global information Long-range dependencies |
| url | https://doi.org/10.1007/s40747-024-01622-w |
| work_keys_str_mv | AT zonghuili refinedfeatureenhancementnetworkforobjectdetection AT yongshengdong refinedfeatureenhancementnetworkforobjectdetection |