Skip to main content
. 2021 Apr 14;16(4):e0247388. doi: 10.1371/journal.pone.0247388

Fig 3.

Fig 3

Comparing the Res2Net and ResNet blocks (with a scale dimension of k = 4): (a) The conventional building block in CNN variants. (b) Res2Net uses a group of 3×3 filters. (c) The SA module adds the attention module to enforce the scale-attention capability.