Automated Natural Language Explanation of Deep Visual Neurons with Large Models

TL;DR

This paper introduces an automated framework using large foundation models to generate semantic explanations of neurons in deep vision networks, enhancing interpretability without human intervention.

Contribution

It presents a novel post-hoc method that automates neuron interpretation across different architectures and datasets, reducing reliance on human input.

Findings

Framework effectively generates semantic neuron explanations

Compatible with multiple model architectures and datasets

Validated through qualitative and quantitative analyses

Abstract

Deep neural networks have exhibited remarkable performance across a wide range of real-world tasks. However, comprehending the underlying reasons for their effectiveness remains a challenging problem. Interpreting deep neural networks through examining neurons offers distinct advantages when it comes to exploring the inner workings of neural networks. Previous research has indicated that specific neurons within deep vision networks possess semantic meaning and play pivotal roles in model performance. Nonetheless, the current methods for generating neuron semantics heavily rely on human intervention, which hampers their scalability and applicability. To address this limitation, this paper proposes a novel post-hoc framework for generating semantic explanations of neurons with large foundation models, without requiring human intervention or prior knowledge. Our framework is designed to be compatible with various model architectures and datasets, facilitating automated and scalable neuron interpretation. Experiments are conducted with both qualitative and quantitative analysis to verify the effectiveness of our proposed approach.