Aggregated Residual Transformations for Deep Neural Networks

• Published in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) pp. 5987 - 5995
• Main Authors: Saining Xie, Girshick, Ross, Dollar, Piotr, Zhuowen Tu, Kaiming He
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2017
• Subjects: Complexity theory; Computer architecture; Network topology; Neural networks; Neurons; Topology

We present a simple, highly modularized network architecture for image classification. Our network is constructed by repeating a building block that aggregates a set of transformations with the same topology. Our simple design results in a homogeneous, multi-branch architecture that has only a few h...