ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees

2026-02-04

AI Summary

This work addresses the limitations of existing hierarchical Shapley methods, which overlook the multi-scale structure inherent in images, resulting in slow convergence, weak semantic alignment, and data-agnostic hierarchical partitions. To overcome these issues, the paper introduces, for the first time, a data-driven binary partition tree (BPT) into the hierarchical Shapley framework, thereby constructing a multi-scale hierarchy that aligns with the intrinsic morphological structure of images. This approach enables efficient and semantically coherent pixel-level feature attribution. The proposed method significantly outperforms current techniques in both computational efficiency and structural alignment, and achieves higher user preference in a study involving 20 participants.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Ensemble Methods
• Knowledge Representation and Reasoning: Preferences

Application Category

• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Security and Privacy: Data transparency and provenance

Abstract

Pixel-level feature attributions are an important tool in eXplainable AI for Computer Vision (XCV), providing visual insights into how image features influence model predictions. The Owen formula for hierarchical Shapley values has been widely used to interpret machine learning (ML) models and their learned representations. However, existing hierarchical Shapley approaches do not exploit the multiscale structure of image data, leading to slow convergence and weak alignment with the actual morphological features. Moreover, no prior Shapley method has leveraged data-aware hierarchies for Computer Vision tasks, leaving a gap in model interpretability of structured visual data. To address this, this paper introduces ShapBPT, a novel data-aware XCV method based on the hierarchical Shapley formula. ShapBPT assigns Shapley coefficients to a multiscale hierarchical structure tailored for images, the Binary Partition Tree (BPT). By using this data-aware hierarchical partitioning, ShapBPT ensures that feature attributions align with intrinsic image morphology, effectively prioritizing relevant regions while reducing computational overhead. This advancement connects hierarchical Shapley methods with image data, providing a more efficient and semantically meaningful approach to visual interpretability. Experimental results confirm ShapBPT's effectiveness, demonstrating superior alignment with image structures and improved efficiency over existing XCV methods, and a 20-subject user study confirming that ShapBPT explanations are preferred by humans.

Problem

• feature attribution
• explainable AI
• hierarchical Shapley values
• image morphology
• data-aware hierarchy

Innovation

• ShapBPT
• hierarchical Shapley values
• Binary Partition Tree
• data-aware hierarchy
• feature attribution