Global-Local Processing in Convolutional Neural Networks

TL;DR

This paper introduces the Global Advantage Stream (GAS), a module that enhances CNNs by capturing global features, improving accuracy and robustness while maintaining efficiency, inspired by human visual perception.

Contribution

The paper proposes a novel plug-and-play module called GAS that enables CNNs to learn holistic features, addressing their local bias and improving performance and robustness.

Findings

GAS improves CNN accuracy with minimal additional computational cost.

The model becomes more robust to adversarial attacks.

It learns more holistic, human-like representations.

Abstract

Convolutional Neural Networks (CNNs) have achieved outstanding performance on image processing challenges. Actually, CNNs imitate the typically developed human brain structures at the micro-level (Artificial neurons). At the same time, they distance themselves from imitating natural visual perception in humans at the macro architectures (high-level cognition). Recently it has been investigated that CNNs are highly biased toward local features and fail to detect the global aspects of their input. Nevertheless, the literature offers limited clues on this problem. To this end, we propose a simple yet effective solution inspired by the unconscious behavior of the human pupil. We devise a simple module called Global Advantage Stream (GAS) to learn and capture the holistic features of input samples (i.e., the global features). Then, the GAS features were combined with a CNN network as a plug-and-play component called the Global/Local Processing (GLP) model. The experimental results confirm that this stream improves the accuracy with an insignificant additional computational/temporal load and makes the network more robust to adversarial attacks. Furthermore, investigating the interpretation of the model shows that it learns a more holistic representation similar to the perceptual system of healthy humans