Enhancing Vision Transformer Explainability Using Artificial Astrocytes

TL;DR

This paper introduces ViTA, a training-free method inspired by neuroscience that improves the explainability of pretrained Vision Transformers by making their explanations more aligned with human perception, validated through multiple XAI techniques.

Contribution

The paper proposes a novel, neuroscience-inspired, training-free approach called ViTA that enhances the explainability of pretrained Vision Transformers without additional training.

Findings

Artificial astrocytes improve explanation alignment with human perception.

Significant improvements across all evaluated XAI techniques.

Enhanced heatmap similarity to ground truth in experiments.

Abstract

Machine learning models achieve high precision, but their decision-making processes often lack explainability. Furthermore, as model complexity increases, explainability typically decreases. Existing efforts to improve explainability primarily involve developing new eXplainable artificial intelligence (XAI) techniques or incorporating explainability constraints during training. While these approaches yield specific improvements, their applicability remains limited. In this work, we propose the Vision Transformer with artificial Astrocytes (ViTA). This training-free approach is inspired by neuroscience and enhances the reasoning of a pretrained deep neural network to generate more human-aligned explanations. We evaluated our approach employing two well-known XAI techniques, Grad-CAM and Grad-CAM++, and compared it to a standard Vision Transformer (ViT). Using the ClickMe dataset, we quantified the similarity between the heatmaps produced by the XAI techniques and a (human-aligned) ground truth. Our results consistently demonstrate that incorporating artificial astrocytes enhances the alignment of model explanations with human perception, leading to statistically significant improvements across all XAI techniques and metrics utilized.