Design of Kernels in Convolutional Neural Networks for Image Classification

TL;DR

This paper investigates how the shape of convolution kernels in CNNs influences learned features and classification performance, proposing a novel kernel design that improves accuracy and robustness while reducing computational costs.

Contribution

It introduces a new kernel shape design for CNNs based on receptive field analysis, achieving state-of-the-art results and enhanced robustness in image classification tasks.

Findings

Achieved state-of-the-art accuracy on ILSVRC-2012 and CIFAR datasets.

Reduced model parameters and computational time.

Improved robustness to occlusion in image classification.

Abstract

Despite the effectiveness of Convolutional Neural Networks (CNNs) for image classification, our understanding of the relationship between shape of convolution kernels and learned representations is limited. In this work, we explore and employ the relationship between shape of kernels which define Receptive Fields (RFs) in CNNs for learning of feature representations and image classification. For this purpose, we first propose a feature visualization method for visualization of pixel-wise classification score maps of learned features. Motivated by our experimental results, and observations reported in the literature for modeling of visual systems, we propose a novel design of shape of kernels for learning of representations in CNNs. In the experimental results, we achieved a state-of-the-art classification performance compared to a base CNN model [28] by reducing the number of parameters and computational time of the model using the ILSVRC-2012 dataset [24]. The proposed models also outperform the state-of-the-art models employed on the CIFAR-10/100 datasets [12] for image classification. Additionally, we analyzed the robustness of the proposed method to occlusion for classification of partially occluded images compared with the state-of-the-art methods. Our results indicate the effectiveness of the proposed approach. The code is available in github.com/minogame/caffe-qhconv.