Embedding of FRPN in CNN architecture
This work addresses the need for more efficient neural network architectures in computer vision, offering a method to achieve equivalent performance with fewer parameters, though it appears incremental as it builds on existing FRPN concepts.
The paper tackled the problem of extending fully recursive perceptron networks (FRPNs) to convolutional neural networks (CNNs) for image classification, resulting in a C-FRPN architecture that consistently outperforms standard CNNs with the same number of parameters, particularly showing large performance gains for small networks.
This paper extends the fully recursive perceptron network (FRPN) model for vectorial inputs to include deep convolutional neural networks (CNNs) which can accept multi-dimensional inputs. A FRPN consists of a recursive layer, which, given a fixed input, iteratively computes an equilibrium state. The unfolding realized with this kind of iterative mechanism allows to simulate a deep neural network with any number of layers. The extension of the FRPN to CNN results in an architecture, which we call convolutional-FRPN (C-FRPN), where the convolutional layers are recursive. The method is evaluated on several image classification benchmarks. It is shown that the C-FRPN consistently outperforms standard CNNs having the same number of parameters. The gap in performance is particularly large for small networks, showing that the C-FRPN is a very powerful architecture, since it allows to obtain equivalent performance with fewer parameters when compared with deep CNNs.