Research Article
Lightweight Real-Time Image Semantic Segmentation Network Based on Multi-Resolution Hybrid Attention Mechanism
Figure 2
(a) denotes the D-ResNet structure, where is the auxiliary loss. (b) denotes the structure of Layer 1. (c) denotes the structure of Layer 2, 3, 4. (d) denotes the structure of Basic Block.
(a) |
(b) |
(c) |
(d) |