Explaining Human Comparisons using Alignment-Importance Heatmaps

TL;DR

This paper introduces Alignment Importance Score heatmaps to explain human comparison tasks by highlighting image features that influence similarity judgments, improving prediction accuracy and interpretability.

Contribution

The paper proposes a novel AIS-based heatmap method that links DNN features to human similarity judgments, enhancing explainability and prediction accuracy.

Findings

AIS improves prediction of human similarity judgments.

Heatmaps visually indicate important image regions for comparisons.

Some relevant features are not visually salient, revealing complex comparison cues.

Abstract

We present a computational explainability approach for human comparison tasks, using Alignment Importance Score (AIS) heatmaps derived from deep-vision models. The AIS reflects a feature-map's unique contribution to the alignment between Deep Neural Network's (DNN) representational geometry and that of humans. We first validate the AIS by showing that prediction of out-of-sample human similarity judgments is improved when constructing representations using only higher-scoring AIS feature maps identified from a training set. We then compute image-specific heatmaps that visually indicate the areas that correspond to feature-maps with higher AIS scores. These maps provide an intuitive explanation of which image areas are more important when it is compared to other images in a cohort. We observe a correspondence between these heatmaps and saliency maps produced by a gaze-prediction model. However, in some cases, meaningful differences emerge, as the dimensions relevant for comparison are not necessarily the most visually salient. To conclude, Alignment Importance improves prediction of human similarity judgments from DNN embeddings, and provides interpretable insights into the relevant information in image space.