Cross-Model Consensus of Explanations and Beyond for Image Classification Models: An Empirical Study

TL;DR

This empirical study investigates common features used by various image classification models through cross-model explanation consensus, revealing correlations with model performance and interpretability.

Contribution

The paper introduces a novel cross-model consensus method for explanations, highlighting shared features among models and their relation to performance and interpretability.

Findings

Consensus explanations align with semantic segmentation ground truth.

Higher consensus scores correlate with better model performance.

Consensus scores are indicative of model interpretability.

Abstract

Existing interpretation algorithms have found that, even deep models make the same and right predictions on the same image, they might rely on different sets of input features for classification. However, among these sets of features, some common features might be used by the majority of models. In this paper, we are wondering what are the common features used by various models for classification and whether the models with better performance may favor those common features. For this purpose, our works uses an interpretation algorithm to attribute the importance of features (e.g., pixels or superpixels) as explanations, and proposes the cross-model consensus of explanations to capture the common features. Specifically, we first prepare a set of deep models as a committee, then deduce the explanation for every model, and obtain the consensus of explanations across the entire committee through voting. With the cross-model consensus of explanations, we conduct extensive experiments using 80+ models on 5 datasets/tasks. We find three interesting phenomena as follows: (1) the consensus obtained from image classification models is aligned with the ground truth of semantic segmentation; (2) we measure the similarity of the explanation result of each model in the committee to the consensus (namely consensus score), and find positive correlations between the consensus score and model performance; and (3) the consensus score coincidentally correlates to the interpretability.