Partial Atrous Cascade R-CNN
Deep-learning-based segmentation methods have achieved excellent results. As two main tasks in computer vision, instance segmentation and semantic segmentation are closely related and mutually beneficial. Spatial context information from the semantic features can also improve the accuracy of instanc...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/11/8/1241 |
| _version_ | 1797434854106726400 |
|---|---|
| author | Mofan Cheng Cien Fan Liqiong Chen Lian Zou Jiale Wang Yifeng Liu Hu Yu |
| author_facet | Mofan Cheng Cien Fan Liqiong Chen Lian Zou Jiale Wang Yifeng Liu Hu Yu |
| author_sort | Mofan Cheng |
| collection | DOAJ |
| description | Deep-learning-based segmentation methods have achieved excellent results. As two main tasks in computer vision, instance segmentation and semantic segmentation are closely related and mutually beneficial. Spatial context information from the semantic features can also improve the accuracy of instance segmentation. Inspired by this, we propose a novel instance segmentation framework named partial atrous cascade R-CNN (PAC), which effectively improves the accuracy of the segmentation boundary. The proposed network innovates in two aspects: (1) A semantic branch with a partial atrous spatial pyramid extraction (PASPE) module is proposed in this paper. The module consists of atrous convolution layers with multi-dilation rates. By expanding the receptive field of the convolutional layer, multi-scale semantic features are greatly enriched. Experiments shows that the new branch obtains more accurate segmentation contours. (2) The proposed mask quality (MQ) module scores the intersection over union (IoU) between the predicted mask and the ground truth mask. Benefiting from the modified mask quality score, the quality of the segmentation results is judged credibly. Our proposed network is trained and tested on the MS COCO dataset. Compared with the benchmark, it brings consistent and noticeable improvements in the case of using the same backbone. |
| first_indexed | 2024-03-09T10:38:53Z |
| format | Article |
| id | doaj.art-aebe840436f04b808d3f14d07c101731 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-03-09T10:38:53Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-aebe840436f04b808d3f14d07c1017312023-12-01T20:47:10ZengMDPI AGElectronics2079-92922022-04-01118124110.3390/electronics11081241Partial Atrous Cascade R-CNNMofan Cheng0Cien Fan1Liqiong Chen2Lian Zou3Jiale Wang4Yifeng Liu5Hu Yu6School of Electronic Information, Wuhan University, Wuhan 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan 430072, ChinaSchool of Electronic Information, Wuhan University, Wuhan 430072, ChinaNational Engineering Laboratory for Risk Perception and Prevention (NEL-RPP), Beijing 100041, ChinaSchool of Electronic Information, Wuhan University, Wuhan 430072, ChinaDeep-learning-based segmentation methods have achieved excellent results. As two main tasks in computer vision, instance segmentation and semantic segmentation are closely related and mutually beneficial. Spatial context information from the semantic features can also improve the accuracy of instance segmentation. Inspired by this, we propose a novel instance segmentation framework named partial atrous cascade R-CNN (PAC), which effectively improves the accuracy of the segmentation boundary. The proposed network innovates in two aspects: (1) A semantic branch with a partial atrous spatial pyramid extraction (PASPE) module is proposed in this paper. The module consists of atrous convolution layers with multi-dilation rates. By expanding the receptive field of the convolutional layer, multi-scale semantic features are greatly enriched. Experiments shows that the new branch obtains more accurate segmentation contours. (2) The proposed mask quality (MQ) module scores the intersection over union (IoU) between the predicted mask and the ground truth mask. Benefiting from the modified mask quality score, the quality of the segmentation results is judged credibly. Our proposed network is trained and tested on the MS COCO dataset. Compared with the benchmark, it brings consistent and noticeable improvements in the case of using the same backbone.https://www.mdpi.com/2079-9292/11/8/1241convolutional neural networkinstance segmentationpartial atrous spatial pyramid extractionmask quality |
| spellingShingle | Mofan Cheng Cien Fan Liqiong Chen Lian Zou Jiale Wang Yifeng Liu Hu Yu Partial Atrous Cascade R-CNN Electronics convolutional neural network instance segmentation partial atrous spatial pyramid extraction mask quality |
| title | Partial Atrous Cascade R-CNN |
| title_full | Partial Atrous Cascade R-CNN |
| title_fullStr | Partial Atrous Cascade R-CNN |
| title_full_unstemmed | Partial Atrous Cascade R-CNN |
| title_short | Partial Atrous Cascade R-CNN |
| title_sort | partial atrous cascade r cnn |
| topic | convolutional neural network instance segmentation partial atrous spatial pyramid extraction mask quality |
| url | https://www.mdpi.com/2079-9292/11/8/1241 |
| work_keys_str_mv | AT mofancheng partialatrouscascadercnn AT cienfan partialatrouscascadercnn AT liqiongchen partialatrouscascadercnn AT lianzou partialatrouscascadercnn AT jialewang partialatrouscascadercnn AT yifengliu partialatrouscascadercnn AT huyu partialatrouscascadercnn |