NeuroTreeNet: A New Method to Explore Horizontal Expansion Network
This addresses the problem of parameter efficiency in neural networks for computer vision researchers, though it appears incremental as it builds on existing horizontal expansion concepts.
The authors tackled the problem of improving neural network performance through horizontal expansion rather than depth, proposing NeuroTreeNet which combines random forest and Inception Model structures to reduce parameters while achieving better performance in super-resolution reconstruction tasks compared to networks with similar parameter counts.
It is widely recognized that the deeper networks or networks with more feature maps have better performance. Existing studies mainly focus on extending the network depth and increasing the feature maps of networks. At the same time, horizontal expansion network (e.g. Inception Model) as an alternative way to improve network performance has not been fully investigated. Accordingly, we proposed NeuroTreeNet (NTN), as a new horizontal extension network through the combination of random forest and Inception Model. Based on the tree structure, in which each branch represents a network and the root node features are shared to child nodes, network parameters are effectively reduced. By combining all features of leaf nodes, even less feature maps achieved better performance. In addition, the relationship between tree structure and the performance of NTN was investigated in depth. Comparing to other networks (e.g. VDSR\_5) with equal magnitude parameters, our model showed preferable performance in super resolution reconstruction task.