NeuRN: Neuro-inspired Domain Generalization for Image Classification

TL;DR

This paper introduces NeuRN, a neuro-inspired normalization layer for deep learning models that improves cross-domain image classification by drawing inspiration from mammalian visual cortex neurons.

Contribution

The paper proposes NeuRN, a novel neuro-inspired layer, and a method using Needleman-Wunsch for architecture similarity, advancing domain generalization in image classification.

Findings

NeuRN improves cross-domain classification accuracy.

NeuRN outperforms baseline models in experiments.

The Needleman-Wunsch based architecture similarity method effectively shortlists promising models.

Abstract

Domain generalization in image classification is a crucial challenge, with models often failing to generalize well across unseen datasets. We address this issue by introducing a neuro-inspired Neural Response Normalization (NeuRN) layer which draws inspiration from neurons in the mammalian visual cortex, which aims to enhance the performance of deep learning architectures on unseen target domains by training deep learning models on a source domain. The performance of these models is considered as a baseline and then compared against models integrated with NeuRN on image classification tasks. We perform experiments across a range of deep learning architectures, including ones derived from Neural Architecture Search and Vision Transformer. Additionally, in order to shortlist models for our experiment from amongst the vast range of deep neural networks available which have shown promising results, we also propose a novel method that uses the Needleman-Wunsch algorithm to compute similarity between deep learning architectures. Our results demonstrate the effectiveness of NeuRN by showing improvement against baseline in cross-domain image classification tasks. Our framework attempts to establish a foundation for future neuro-inspired deep learning models.