MGSeg: Multiple Granularity-Based Real-Time Semantic Segmentation Network
| Autor: | Shi-Hua Liang, Jun-Yan He, Bo Zhao, Lei Zhang, Xiao Wu |
|---|---|
| Rok vydání: | 2021 |
| Předmět: | |
| Zdroj: | IEEE Transactions on Image Processing. 30:7200-7214 |
| ISSN: | 1941-0042 1057-7149 |
| DOI: | 10.1109/tip.2021.3102509 |
| Popis: | Recent works on semantic segmentation witness significant performance improvement by utilizing global contextual information. In this paper, an efficient multi-granularity based semantic segmentation network (MGSeg) is proposed for real-time semantic segmentation, by modeling the latent relevance between multi-scale geometric details and high-level semantics for fine granularity segmentation. In particular, a light-weight backbone ResNet-18 is first adopted to produce the hierarchical features. Hybrid Attention Feature Aggregation (HAFA) is designed to filter the noisy spatial details of features, acquire the scale-invariance representation, and alleviate the gradient vanishing problem of the early-stage feature learning. After aggregating the learned features, Fine Granularity Refinement (FGR) module is employed to explicitly model the relationship between the multi-level features and categories, generating proper weights for fusion. More importantly, to meet the real-time processing, a series of light-weight strategies and simplified structures are applied to accelerate the efficiency, including light-weight backbone, channel compression, narrow neck structure, and so on. Extensive experiments conducted on benchmark datasets Cityscapes and CamVid demonstrate that the proposed method achieves the state-of-the-art performance, 77.8%@50fps and 72.7%@127fps on Cityscapes and CamVid datasets, respectively, having the capability for real-time applications. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|