![[2602.07047] ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees](https://arxiv.org/static/browse/0.3.4/images/arxiv-logo-fb.png){kind=logo}
[2602.07047] ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees
Summary
The paper introduces ShapBPT, a novel method for image feature attributions using data-aware binary partition trees, enhancing interpretability in computer vision.
Why It Matters
ShapBPT addresses limitations in existing hierarchical Shapley methods by leveraging multiscale image structures, improving model interpretability and computational efficiency in eXplainable AI for Computer Vision. This advancement is crucial for developing more reliable AI systems that can be understood and trusted by users.
Key Takeaways
- ShapBPT improves pixel-level feature attributions in computer vision.
- Utilizes a data-aware hierarchical structure for enhanced interpretability.
- Demonstrates superior efficiency and alignment with image morphology.
- Experimental results show preference for ShapBPT explanations in user studies.
- Addresses gaps in existing Shapley methods for structured visual data.
Computer Science > Computer Vision and Pattern Recognition arXiv:2602.07047 (cs) [Submitted on 4 Feb 2026 (v1), last revised 16 Feb 2026 (this version, v2)] Title:ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees Authors:Muhammad Rashid, Elvio G. Amparore, Enrico Ferrari, Damiano Verda View a PDF of the paper titled ShapBPT: Image Feature Attributions Using Data-Aware Binary Partition Trees, by Muhammad Rashid and 3 other authors View PDF HTML (experimental) 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 ensur...