ChoiceNet: CNN learning through choice of multiple feature map representations

Add code
Apr 20, 2019
Farshid Rayhan, Aphrodite Galata, Timothy F. Cootes
Figure 1 for ChoiceNet: CNN learning through choice of multiple feature map representations
Figure 2 for ChoiceNet: CNN learning through choice of multiple feature map representations
Figure 3 for ChoiceNet: CNN learning through choice of multiple feature map representations
Figure 4 for ChoiceNet: CNN learning through choice of multiple feature map representations

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon

We introduce a new architecture called ChoiceNet where each layer of the network is highly connected with skip connections and channelwise concatenations. This enables the network to alleviate the problem of vanishing gradients, reduces the number of parameters without sacrificing performance, and encourages feature reuse. We evaluate our proposed architecture on three benchmark datasetsforobjectrecognitiontasks(CIFAR-10,CIFAR100, SVHN) and on a semantic segmentation dataset (CamVid).

View paper onarxiv icon

Share this with someone who'll enjoy it:

Twitter IconFacebook IconLinkedin IconWhatsapp IconMessenger Icon