On the ability of CNNs to extract color invariant intensity based features for image classification

TL;DR

This paper examines how CNNs can be made more robust to color variations in images by using architectural modifications and regularization techniques, aiming to improve their reliance on invariant features.

Contribution

It introduces a novel architectural modification with dropout regularization that enhances CNNs' focus on color-invariant intensity features for better classification.

Findings

Color changes significantly impact CNN classification accuracy.

The proposed dropout technique improves reliance on invariant features.

Regularization techniques influence generalization across color-modified datasets.

Abstract

Convolutional neural networks (CNNs) have demonstrated remarkable success in vision-related tasks. However, their susceptibility to failing when inputs deviate from the training distribution is well-documented. Recent studies suggest that CNNs exhibit a bias toward texture instead of object shape in image classification tasks, and that background information may affect predictions. This paper investigates the ability of CNNs to adapt to different color distributions in an image while maintaining context and background. The results of our experiments on modified MNIST and FashionMNIST data demonstrate that changes in color can substantially affect classification accuracy. The paper explores the effects of various regularization techniques on generalization error across datasets and proposes a minor architectural modification utilizing the dropout regularization in a novel way that enhances model reliance on color-invariant intensity-based features for improved classification accuracy. Overall, this work contributes to ongoing efforts to understand the limitations and challenges of CNNs in image classification tasks and offers potential solutions to enhance their performance.