Attention, Please! PixelSHAP Reveals What Vision-Language Models Actually Focus On

📅 2025-03-09
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work addresses the insufficient interpretability of vision-language models (VLMs) in high-stakes applications. We propose PixelSHAP—the first model-agnostic, pixel-level attribution framework specifically designed for VLMs. PixelSHAP extends Shapley value theory to structured visual entities by introducing zero-shot object masking and recomposition, embedding-space similarity measurement, and an efficient sampling strategy to quantify each pixel’s contribution to VLM outputs—thereby jointly supporting semantic object-level understanding and precise pixel-level localization. Crucially, it operates without access to model parameters or gradients, enabling black-box interpretation of commercial VLMs. Evaluated on real-world high-risk scenarios—including autonomous driving—PixelSHAP successfully identifies critical visual drivers underlying model decisions, substantially enhancing transparency and trust. An open-source implementation demonstrates strong cross-model robustness and practical utility across diverse VLM architectures.

Technology Category

Application Category

📝 Abstract
Interpretability in Vision-Language Models (VLMs) is crucial for trust, debugging, and decision-making in high-stakes applications. We introduce PixelSHAP, a model-agnostic framework extending Shapley-based analysis to structured visual entities. Unlike previous methods focusing on text prompts, PixelSHAP applies to vision-based reasoning by systematically perturbing image objects and quantifying their influence on a VLM's response. PixelSHAP requires no model internals, operating solely on input-output pairs, making it compatible with open-source and commercial models. It supports diverse embedding-based similarity metrics and scales efficiently using optimization techniques inspired by Shapley-based methods. We validate PixelSHAP in autonomous driving, highlighting its ability to enhance interpretability. Key challenges include segmentation sensitivity and object occlusion. Our open-source implementation facilitates further research.
Problem

Research questions and friction points this paper is trying to address.

Enhances interpretability in Vision-Language Models (VLMs).
Quantifies influence of image objects on VLM responses.
Supports diverse embedding-based similarity metrics efficiently.
Innovation

Methods, ideas, or system contributions that make the work stand out.

PixelSHAP extends Shapley analysis to visual entities
Systematically perturbs image objects for VLM interpretability
Operates on input-output pairs without model internals
🔎 Similar Papers