Biologically inspired deep residual networks for computer vision applications
This work addresses the need for better generalization in computer vision models, but it is incremental as it builds on existing ResNet frameworks with a minor architectural change.
The authors tackled the problem of improving image classification accuracy in deep residual networks by introducing hexagonal convolutions along skip connections, resulting in average improvements of 1.35% on ImageNet 2012 and 0.48% on CIFAR-10 compared to baseline ResNet architectures.
Deep neural network has been ensured as a key technology in the field of many challenging and vigorously researched computer vision tasks. Furthermore, classical ResNet is thought to be a state-of-the-art convolutional neural network (CNN) and was observed to capture features which can have good generalization ability. In this work, we propose a biologically inspired deep residual neural network where the hexagonal convolutions are introduced along the skip connections. The performance of different ResNet variants using square and hexagonal convolution are evaluated with the competitive training strategy mentioned by [1]. We show that the proposed approach advances the baseline image classification accuracy of vanilla ResNet architectures on CIFAR-10 and the same was observed over multiple subsets of the ImageNet 2012 dataset. We observed an average improvement by 1.35% and 0.48% on baseline top-1 accuracies for ImageNet 2012 and CIFAR-10, respectively. The proposed biologically inspired deep residual networks were observed to have improved generalized performance and this could be a potential research direction to improve the discriminative ability of state-of-the-art image classification networks.