Multi-Scale Receptive Field Detection Network
Deep convolutional neural networks have contributed much to various computer vision problems including object detection. However, there are still many problems to be solved. Scale variation across object instances is one of the major challenges for object detection. In this paper, we propose a multi...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2019-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/8843869/ |
| _version_ | 1811212295071596544 |
|---|---|
| author | Haoren Cui Zhihua Wei |
| author_facet | Haoren Cui Zhihua Wei |
| author_sort | Haoren Cui |
| collection | DOAJ |
| description | Deep convolutional neural networks have contributed much to various computer vision problems including object detection. However, there are still many problems to be solved. Scale variation across object instances is one of the major challenges for object detection. In this paper, we propose a multi-scale receptive field detection network (MS-RFDN), a one-stage approach to detect objects of different scales in the image. The proposed network combines predictions of different scales from feature maps of different scales and receptive fields. To generate s scale-specific feature maps in specific layer, we design a scale-specific concatenation module (SSC module). This scale-specific feature maps are merged from the dense block and dilated block, which has the same size of the receptive field. Through our multi-scale layer network structure and scale-specific feature maps, our model has a significant improvement in small object detection. On the VOC 2007 test dataset, our method almost achieves the effect of the state-of-the-art one-stage methods, which confirmed the effectiveness of our model. |
| first_indexed | 2024-04-12T05:26:44Z |
| format | Article |
| id | doaj.art-702bc2ded08841be9116c68d6f6bed32 |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-04-12T05:26:44Z |
| publishDate | 2019-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-702bc2ded08841be9116c68d6f6bed322022-12-22T03:46:15ZengIEEEIEEE Access2169-35362019-01-01713882513883210.1109/ACCESS.2019.29420778843869Multi-Scale Receptive Field Detection NetworkHaoren Cui0https://orcid.org/0000-0001-9187-9783Zhihua Wei1Department of Computer Science and Technology, Tongji University, Shanghai, ChinaDepartment of Computer Science and Technology, Tongji University, Shanghai, ChinaDeep convolutional neural networks have contributed much to various computer vision problems including object detection. However, there are still many problems to be solved. Scale variation across object instances is one of the major challenges for object detection. In this paper, we propose a multi-scale receptive field detection network (MS-RFDN), a one-stage approach to detect objects of different scales in the image. The proposed network combines predictions of different scales from feature maps of different scales and receptive fields. To generate s scale-specific feature maps in specific layer, we design a scale-specific concatenation module (SSC module). This scale-specific feature maps are merged from the dense block and dilated block, which has the same size of the receptive field. Through our multi-scale layer network structure and scale-specific feature maps, our model has a significant improvement in small object detection. On the VOC 2007 test dataset, our method almost achieves the effect of the state-of-the-art one-stage methods, which confirmed the effectiveness of our model.https://ieeexplore.ieee.org/document/8843869/Object detectionreceptive fieldscale variation |
| spellingShingle | Haoren Cui Zhihua Wei Multi-Scale Receptive Field Detection Network IEEE Access Object detection receptive field scale variation |
| title | Multi-Scale Receptive Field Detection Network |
| title_full | Multi-Scale Receptive Field Detection Network |
| title_fullStr | Multi-Scale Receptive Field Detection Network |
| title_full_unstemmed | Multi-Scale Receptive Field Detection Network |
| title_short | Multi-Scale Receptive Field Detection Network |
| title_sort | multi scale receptive field detection network |
| topic | Object detection receptive field scale variation |
| url | https://ieeexplore.ieee.org/document/8843869/ |
| work_keys_str_mv | AT haorencui multiscalereceptivefielddetectionnetwork AT zhihuawei multiscalereceptivefielddetectionnetwork |