ResNetX: a more disordered and deeper network architecture
This work addresses the need for better theoretical understanding and architectural design in neural networks, but it is incremental as it builds directly on ResNet with modest gains.
The authors tackled the problem of theoretically characterizing how network structure influences performance by introducing ResNetX, a more disordered and deeper architecture that extends ResNet through folding techniques, resulting in improved image classification on CIFAR-10 and CIFAR-100 benchmarks.
Designing efficient network structures has always been the core content of neural network research. ResNet and its variants have proved to be efficient in architecture. However, how to theoretically character the influence of network structure on performance is still vague. With the help of techniques in complex networks, We here provide a natural yet efficient extension to ResNet by folding its backbone chain. Our architecture has two structural features when being mapped to directed acyclic graphs: First is a higher degree of the disorder compared with ResNet, which let ResNetX explore a larger number of feature maps with different sizes of receptive fields. Second is a larger proportion of shorter paths compared to ResNet, which improves the direct flow of information through the entire network. Our architecture exposes a new dimension, namely "fold depth", in addition to existing dimensions of depth, width, and cardinality. Our architecture is a natural extension to ResNet, and can be integrated with existing state-of-the-art methods with little effort. Image classification results on CIFAR-10 and CIFAR-100 benchmarks suggested that our new network architecture performs better than ResNet.