Multi-Semantic Image Recognition Model and Evaluating Index for explaining the deep learning models

TL;DR

This paper introduces a multi-semantic image recognition model that enhances interpretability and proposes a new index to quantitatively evaluate the interpretability of deep learning models, addressing the black-box issue.

Contribution

It presents a novel multi-semantic recognition model and an evaluation index for interpretability, advancing understanding of neural network decision processes.

Findings

The model improves interpretability of deep learning decisions.

The evaluation index effectively quantifies model interpretability.

Baseline performance comparisons with state-of-the-art models are provided.

Abstract

Although deep learning models are powerful among various applications, most deep learning models are still a black box, lacking verifiability and interpretability, which means the decision-making process that human beings cannot understand. Therefore, how to evaluate deep neural networks with explanations is still an urgent task. In this paper, we first propose a multi-semantic image recognition model, which enables human beings to understand the decision-making process of the neural network. Then, we presents a new evaluation index, which can quantitatively assess the model interpretability. We also comprehensively summarize the semantic information that affects the image classification results in the judgment process of neural networks. Finally, this paper also exhibits the relevant baseline performance with current state-of-the-art deep learning models.