Pyramidal RoR for Image Classification
This work addresses performance limitations in deep convolutional neural networks for image classification, but it is incremental as it combines existing methods like RoR and PyramidNet.
The paper tackled the problem of information loss in Residual Networks of Residual Networks (RoR) for image classification by proposing a Pyramidal RoR model, achieving state-of-the-art error rates of 2.96% on CIFAR-10, 16.40% on CIFAR-100, and 1.59% on SVHN.
The Residual Networks of Residual Networks (RoR) exhibits excellent performance in the image classification task, but sharply increasing the number of feature map channels makes the characteristic information transmission incoherent, which losses a certain of information related to classification prediction, limiting the classification performance. In this paper, a Pyramidal RoR network model is proposed by analysing the performance characteristics of RoR and combining with the PyramidNet. Firstly, based on RoR, the Pyramidal RoR network model with channels gradually increasing is designed. Secondly, we analysed the effect of different residual block structures on performance, and chosen the residual block structure which best favoured the classification performance. Finally, we add an important principle to further optimize Pyramidal RoR networks, drop-path is used to avoid over-fitting and save training time. In this paper, image classification experiments were performed on CIFAR-10/100 and SVHN datasets, and we achieved the current lowest classification error rates were 2.96%, 16.40% and 1.59%, respectively. Experiments show that the Pyramidal RoR network optimization method can improve the network performance for different data sets and effectively suppress the gradient disappearance problem in DCNN training.