Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation
Abstract Semantic segmentation is crucial to the autonomous driving, as an accurate recognition and location of the surrounding scenes can be provided for the street scenes understanding task. Many existing segmentation networks usually fuse high‐level and low‐level features to boost segmentation pe...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2021-09-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cvi2.12026 |
| _version_ | 1798041283893133312 |
|---|---|
| author | Jie Hu Huifang Kong Lei Fan Jun Zhou |
| author_facet | Jie Hu Huifang Kong Lei Fan Jun Zhou |
| author_sort | Jie Hu |
| collection | DOAJ |
| description | Abstract Semantic segmentation is crucial to the autonomous driving, as an accurate recognition and location of the surrounding scenes can be provided for the street scenes understanding task. Many existing segmentation networks usually fuse high‐level and low‐level features to boost segmentation performance. However, the simple fusion may impose a limited performance improvement because of the gap between high‐level and low‐level features. To alleviate this limitation, we respectively propose spatial aggregation and channel fusion to bridge the gap. Our implementation, inspired by the attention mechanism, consists of two steps: (1) Spatial aggregation relies on the proposed pyramid spatial context aggregation module to capture spatial similarities to enhance the spatial representation of high‐level features, which is more effective for the latter fusion. (2) Channel fusion relies on the proposed attention‐based channel fusion module to weight channel maps on different levels to enhance the fusion. In addition, the complete network with U‐shape structure is constructed. A series of ablation experiments are conducted to demonstrate the effectiveness of our designs, and the network achieves mIoU score of 81.4% on Cityscapes test dataset and 84.6% on PASCALVOC 2012 test dataset. |
| first_indexed | 2024-04-11T22:19:22Z |
| format | Article |
| id | doaj.art-a6aebdc37c794aec9a2dc4ad4282edec |
| institution | Directory Open Access Journal |
| issn | 1751-9632 1751-9640 |
| language | English |
| last_indexed | 2024-04-11T22:19:22Z |
| publishDate | 2021-09-01 |
| publisher | Wiley |
| record_format | Article |
| series | IET Computer Vision |
| spelling | doaj.art-a6aebdc37c794aec9a2dc4ad4282edec2022-12-22T04:00:14ZengWileyIET Computer Vision1751-96321751-96402021-09-0115641842710.1049/cvi2.12026Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentationJie Hu0Huifang Kong1Lei Fan2Jun Zhou3School of Electrical Engineering and Automation Hefei University of Technology Hefei ChinaSchool of Electrical Engineering and Automation Hefei University of Technology Hefei ChinaSchool of Electrical Engineering and Automation Hefei University of Technology Hefei ChinaSchool of Electrical Engineering and Automation Hefei University of Technology Hefei ChinaAbstract Semantic segmentation is crucial to the autonomous driving, as an accurate recognition and location of the surrounding scenes can be provided for the street scenes understanding task. Many existing segmentation networks usually fuse high‐level and low‐level features to boost segmentation performance. However, the simple fusion may impose a limited performance improvement because of the gap between high‐level and low‐level features. To alleviate this limitation, we respectively propose spatial aggregation and channel fusion to bridge the gap. Our implementation, inspired by the attention mechanism, consists of two steps: (1) Spatial aggregation relies on the proposed pyramid spatial context aggregation module to capture spatial similarities to enhance the spatial representation of high‐level features, which is more effective for the latter fusion. (2) Channel fusion relies on the proposed attention‐based channel fusion module to weight channel maps on different levels to enhance the fusion. In addition, the complete network with U‐shape structure is constructed. A series of ablation experiments are conducted to demonstrate the effectiveness of our designs, and the network achieves mIoU score of 81.4% on Cityscapes test dataset and 84.6% on PASCALVOC 2012 test dataset.https://doi.org/10.1049/cvi2.12026image fusionimage segmentationmobile robotsobject recognitionrobot vision |
| spellingShingle | Jie Hu Huifang Kong Lei Fan Jun Zhou Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation IET Computer Vision image fusion image segmentation mobile robots object recognition robot vision |
| title | Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation |
| title_full | Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation |
| title_fullStr | Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation |
| title_full_unstemmed | Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation |
| title_short | Enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation |
| title_sort | enhancing feature fusion with spatial aggregation and channel fusion for semantic segmentation |
| topic | image fusion image segmentation mobile robots object recognition robot vision |
| url | https://doi.org/10.1049/cvi2.12026 |
| work_keys_str_mv | AT jiehu enhancingfeaturefusionwithspatialaggregationandchannelfusionforsemanticsegmentation AT huifangkong enhancingfeaturefusionwithspatialaggregationandchannelfusionforsemanticsegmentation AT leifan enhancingfeaturefusionwithspatialaggregationandchannelfusionforsemanticsegmentation AT junzhou enhancingfeaturefusionwithspatialaggregationandchannelfusionforsemanticsegmentation |