Avola D, Cinque L, Fagioli A, Foresti GL. SIRe-Networks: Convolutional neural networks architectural extension for information preservation via skip/residual connections and interlaced auto-encoders.
Neural Netw 2022;
153:386-398. [PMID:
35785610 DOI:
10.1016/j.neunet.2022.06.030]
[Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2021] [Revised: 06/23/2022] [Accepted: 06/23/2022] [Indexed: 12/01/2022]
Abstract
Improving existing neural network architectures can involve several design choices such as manipulating the loss functions, employing a diverse learning strategy, exploiting gradient evolution at training time, optimizing the network hyper-parameters, or increasing the architecture depth. The latter approach is a straightforward solution, since it directly enhances the representation capabilities of a network; however, the increased depth generally incurs in the well-known vanishing gradient problem. In this paper, borrowing from different methods addressing this issue, we introduce an interlaced multi-task learning strategy, defined SIRe, to reduce the vanishing gradient in relation to the object classification task. The presented methodology directly improves a convolutional neural network (CNN) by preserving information from the input image through interlaced auto-encoders (AEs), and further refines the base network architecture by means of skip and residual connections. To validate the presented methodology, a simple CNN and various implementations of famous networks are extended via the SIRe strategy and extensively tested on five collections, i.e., MNIST, Fashion-MNIST, CIFAR-10, CIFAR-100, and Caltech-256; where the SIRe-extended architectures achieve significantly increased performances across all models and datasets, thus confirming the presented approach effectiveness.
Collapse