Improved Inception-Residual Convolutional Neural Network for Object Recognition

TL;DR

This paper introduces IRRCNN, a novel deep learning architecture combining Inception, Residual, and Recurrent CNNs, achieving higher recognition accuracy on multiple benchmarks with the same number of parameters.

Contribution

The paper presents a new IRRCNN model that enhances recognition accuracy by integrating recurrent, inception, and residual components, outperforming existing models on standard datasets.

Findings

IRRCNN outperforms RCNN, EIN, and EIRN on CIFAR-100 with around 4.5% accuracy improvement.

IRRCNN achieves higher recognition accuracy on CIFAR-10, TinyImageNet-200, and CU3D-100 datasets.

The proposed architecture generalizes and improves training accuracy of inception, residual, and recurrent networks.

Abstract

Machine learning and computer vision have driven many of the greatest advances in the modeling of Deep Convolutional Neural Networks (DCNNs). Nowadays, most of the research has been focused on improving recognition accuracy with better DCNN models and learning approaches. The recurrent convolutional approach is not applied very much, other than in a few DCNN architectures. On the other hand, Inception-v4 and Residual networks have promptly become popular among computer the vision community. In this paper, we introduce a new DCNN model called the Inception Recurrent Residual Convolutional Neural Network (IRRCNN), which utilizes the power of the Recurrent Convolutional Neural Network (RCNN), the Inception network, and the Residual network. This approach improves the recognition accuracy of the Inception-residual network with same number of network parameters. In addition, this proposed architecture generalizes the Inception network, the RCNN, and the Residual network with significantly improved training accuracy. We have empirically evaluated the performance of the IRRCNN model on different benchmarks including CIFAR-10, CIFAR-100, TinyImageNet-200, and CU3D-100. The experimental results show higher recognition accuracy against most of the popular DCNN models including the RCNN. We have also investigated the performance of the IRRCNN approach against the Equivalent Inception Network (EIN) and the Equivalent Inception Residual Network (EIRN) counterpart on the CIFAR-100 dataset. We report around 4.53%, 4.49% and 3.56% improvement in classification accuracy compared with the RCNN, EIN, and EIRN on the CIFAR-100 dataset respectively. Furthermore, the experiment has been conducted on the TinyImageNet-200 and CU3D-100 datasets where the IRRCNN provides better testing accuracy compared to the Inception Recurrent CNN (IRCNN), the EIN, and the EIRN.