ChoiceNet: CNN learning through choice of multiple feature map representations

20 Apr 2019  ·  Farshid Rayhan, Aphrodite Galata, Timothy F. Cootes ·

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 datasets for object recognition tasks (ImageNet, CIFAR- 10, CIFAR-100, SVHN) and on a semantic segmentation dataset (CamVid).

PDF Abstract

Results from the Paper

  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.


No methods listed for this paper. Add relevant methods here