Relay Backpropagation for Effective Learning of Deep Convolutional Neural Networks
This addresses the issue of training deep networks for computer vision researchers, showing broad applicability beyond specific datasets or architectures.
The paper tackles the problem of performance degradation in deep convolutional neural networks by proposing Relay Backpropagation, a method that enhances effective information propagation during training, achieving first place in the ILSVRC 2015 Scene Classification Challenge.
Learning deeper convolutional neural networks becomes a tendency in recent years. However, many empirical evidences suggest that performance improvement cannot be gained by simply stacking more layers. In this paper, we consider the issue from an information theoretical perspective, and propose a novel method Relay Backpropagation, that encourages the propagation of effective information through the network in training stage. By virtue of the method, we achieved the first place in ILSVRC 2015 Scene Classification Challenge. Extensive experiments on two challenging large scale datasets demonstrate the effectiveness of our method is not restricted to a specific dataset or network architecture. Our models will be available to the research community later.