Lightweight Prediction and Boundary Attention-Based Semantic Segmentation for Road Scene Understanding
- Authors
- Sun, Jee-Young; Jung, Seung-Won; Ko, Sung-Jea
- Issue Date
- 2020
- Publisher
- IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
- Keywords
- Attention mechanism; boundary attention; deep learning; feature refinement; real-time semantic segmentation; residual learning; road scene understanding
- Citation
- IEEE ACCESS, v.8, pp.108449 - 108460
- Indexed
- SCIE
SCOPUS
- Journal Title
- IEEE ACCESS
- Volume
- 8
- Start Page
- 108449
- End Page
- 108460
- URI
- https://scholar.korea.ac.kr/handle/2021.sw.korea/58978
- DOI
- 10.1109/ACCESS.2020.3001679
- ISSN
- 2169-3536
- Abstract
- Semantic segmentation is one of the most commonly used techniques for road scene understanding. Recently developed deep learning-based semantic segmentation networks are typically based on the encoder-decoder structure and have made great progress in road scene understanding. However, these conventional networks still encounter difficulties in recovering spatial details. To overcome this problem, we introduce a lightweight prediction and boundary-aware refinement module that can hierarchically refine the segmentation results with spatial details. The proposed refinement module has two attention units called the upper-level prediction attention unit and the upper-level boundary attention unit. The upper-level prediction attention unit emphasizes the features in the regions that need to be refined by using predicted class probability from the upper-level, whereas the upper-level boundary attention unit focuses on the features near the semantic boundary of the upper-level segmentation result. By using the proposed prediction and boundary-aware refinement module in the decoder network, the segmentation result can gradually be improved in a top-down manner to a finer and more complete one. Experimental results on the Cityscapes and CamVid datasets demonstrate that the proposed prediction and boundary attention-based refinement module can achieve considerable performance improvement in segmentation accuracy with a marginal increase in computational complexity.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Engineering > School of Electrical Engineering > 1. Journal Articles
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.