Why Does It Look There? Structured Explanations for Image Classification

TL;DR

This paper introduces I2X, a framework that creates structured, faithful explanations for image classification models by leveraging prototypes and checkpoints, enhancing interpretability and enabling model improvement.

Contribution

I2X is the first method to generate structured explanations directly from unstructured interpretability, linking prototypes to decision processes during training.

Findings

I2X effectively reveals prototype-based inference in models.

It improves prediction accuracy through targeted sample perturbation.

Demonstrates applicability on MNIST and CIFAR10 datasets.

Abstract

Deep learning models achieve remarkable predictive performance, yet their black-box nature limits transparency and trustworthiness. Although numerous explainable artificial intelligence (XAI) methods have been proposed, they primarily provide saliency maps or concepts (i.e., unstructured interpretability). Existing approaches often rely on auxiliary models (\eg, GPT, CLIP) to describe model behavior, thereby compromising faithfulness to the original models. We propose Interpretability to Explainability (I2X), a framework that builds structured explanations directly from unstructured interpretability by quantifying progress at selected checkpoints during training using prototypes extracted from post-hoc XAI methods (e.g., GradCAM). I2X answers the question of "why does it look there" by providing a structured view of both intra- and inter-class decision making during training. Experiments on MNIST and CIFAR10 demonstrate effectiveness of I2X to reveal prototype-based inference process of various image classification models. Moreover, we demonstrate that I2X can be used to improve predictions across different model architectures and datasets: we can identify uncertain prototypes recognized by I2X and then use targeted perturbation of samples that allows fine-tuning to ultimately improve accuracy. Thus, I2X not only faithfully explains model behavior but also provides a practical approach to guide optimization toward desired targets.