Constrained Linear Data-feature Mapping for Image Classification

23 Nov 2019  ·  Juncai He, Yuyan Chen, Lian Zhang, Jinchao Xu ·

In this paper, we propose a constrained linear data-feature mapping model as an interpretable mathematical model for image classification using convolutional neural network (CNN) such as the ResNet. From this viewpoint, we establish the detailed connections in a technical level between the traditional iterative schemes for constrained linear system and the architecture for the basic blocks of ResNet. Under these connections, we propose some natural modifications of ResNet type models which will have less parameters but still maintain almost the same accuracy as these corresponding original models. Some numerical experiments are shown to demonstrate the validity of this constrained learning data-feature mapping assumption.

PDF Abstract

Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help the community compare results to other papers.

Methods