Skip to main content
. 2024 Apr 12;24(8):2483. doi: 10.3390/s24082483

Figure 2.

Figure 2

FasterNet’s overall architecture. It consists of four hierarchical layers, each containing a stack of FasterNet blocks, with a preceding embed or fusion layer. Feature classification is performed in the last three layers. Within each FasterNet block, two PWConv levels follow one PConv level.