Timezone: »

 
Poster
Cross-channel Communication Networks
Jianwei Yang · Zhile Ren · Chuang Gan · Hongyuan Zhu · Devi Parikh

Thu Dec 12 10:45 AM -- 12:45 PM (PST) @ East Exhibition Hall B + C #146
in Deep Learning -- CNN Architectures »

Convolutional neural networks (CNNs) process input data by feed-forwarding responses to subsequent layers. While a lot of progress has been made by making networks deeper, filters at each layer independently generate responses given the input and do not communicate with each other. In this paper, we introduce a novel network unit called Cross-channel Communication (C3) block, a simple yet effective module to encourage the communication across filters within the same layer. The C3 block enables filters to exchange information through a micro neural network, which consists of a feature encoder, a message passer, and a feature decoder, before sending the information to the next layer. With C3 block, each channel response is modulated by accounting for the responses at other channels. Extensive experiments on multiple vision tasks show that our proposed block brings improvements for different CNN architectures, and learns more diverse and complementary representations.

Keywords: Computer Vision · CNN Architectures · Applications · Deep Learning
[ Paper]  [ Poster] 

Author Information

Jianwei Yang (Georgia Tech)
Zhile Ren (Georgia Tech)
Chuang Gan (MIT-IBM Watson AI Lab)
Hongyuan Zhu (Astar)
Devi Parikh (Georgia Tech / Facebook AI Research (FAIR))

More from the Same Authors