Name
Title | ||
|---|---|---|
Self-Learned Feature Reconstruction and Offset-Dilated Feature Fusion for Real-Time Semantic Segmentation |
Abstract | ||
|---|---|---|
Recent approaches for real-time semantic segmentation usually employ the encoder-decoder architecture as the backbone to generate a high-quality segmentation prediction. There has been a lot of research on designing efficient encoding methods. However, enhancing the performance of components in decoder is also crucial for pixel-level recognition. In this paper, we propose a self-learned feature reconstruction (SFR) method and an offset-dilated feature fusion (ODFF) module to improve the prediction reconstruction capability of the decoder. Concretely, SFR can effectively reconstruct the high-resolution feature maps by recombining feature space, in which the space transformation matrix implicitly contained in a convolution layer can selectively highlight features at each position by leveraging the knowledge of label space in a self-learned way. Moreover, ODFF module can effectively fuse multilevel features with multiscale contextual information by feeding the feature maps into designed parallel offset-dilated convolutions, which enhances the feature representation capability of the decoder. Experiments on Cityscapes and CamVid datasets demonstrate the superior performance of our proposed methods embedded in ESPNet. |
Year | DOI | Venue |
|---|---|---|
2019 | 10.1109/ICTAI.2019.00054 | 2019 IEEE 31st International Conference on Tools with Artificial Intelligence (ICTAI) |
Keywords | Field | DocType |
real-time semantic segmentation,encoder decoder architecture,feature reconstruction,feature fusion | Feature fusion,Feature vector,Pattern recognition,Computer science,Convolution,Segmentation,Matrix (mathematics),Artificial intelligence,Fuse (electrical),Offset (computer science),Encoding (memory) | Conference |
ISSN | ISBN | Citations |
1082-3409 | 978-1-7281-3799-5 | 0 |
PageRank | References | Authors |
0.34 | 5 | 5 |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Gege Qi | 1 | 1 | 1.36 |
| Lin Pan | 2 | 0 | 0.34 |
| Song Liu | 3 | 6 | 2.44 |
| Zhengding Luo | 4 | 1 | 1.36 |
| Zhu Yuesheng | 5 | 112 | 39.21 |