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.
Original language | English |
---|---|
Article number | 9114881 |
Pages (from-to) | 108449-108460 |
Number of pages | 12 |
Journal | IEEE Access |
Volume | 8 |
DOIs | |
Publication status | Published - 2020 |
Keywords
- Attention mechanism
- boundary attention
- deep learning
- feature refinement
- real-time semantic segmentation
- residual learning
- road scene understanding
ASJC Scopus subject areas
- Engineering(all)
- Materials Science(all)
- Electrical and Electronic Engineering
- Computer Science(all)