Skip to main content
. 2020 Dec 16;40(3):1032–1041. doi: 10.1109/TMI.2020.3045295

Fig. 7.

Fig. 7.

The Loss of autoencoder network constructed with ResNet, VGG Net, and our proposed multi-scale attention block. The vanishing gradient that may stick in local optimization and unstable loss appears in VGG Net and ResNet 50/101. The network with only three ours blocks achieve minimum loss, which equals and perhaps surpasses ResNet34. The FPS also proves that our block with simple structure has advantages on detection speed.