模型不确定性校准影响解释可靠性，新方法提升视觉模型解释准确性
Why Uncertainty Calibration Matters for Reliable Perturbation-based Explanations
- 通过校准模型置信度与真实准确率关系，改进扰动解释
- 实验显示校准后解释更贴近人类感知和真实物体位置
- 适合关注可解释性可信度的开发者与研究者
基于扰动的解释广泛用于提升现代机器学习模型的透明性，但其可靠性常因模型在特定扰动下的未知行为而受损。本文研究不确定性校准（即模型置信度与实际准确率的一致性）与扰动解释之间的关系。结果表明，模型在解释专用扰动下常产生不可靠的概率估计，且理论证明这直接损害解释质量。为此，提出ReCalX，一种在不改变原始预测的前提下，针对扰动解释进行模型校准的新方法。在多个主流计算机视觉模型上的实验表明，该校准策略生成的解释更符合人类感知和实际物体位置。
原文摘要 · Abstract (English)
Perturbation-based explanations are widely utilized to enhance the transparency of modern machine-learning models. However, their reliability is often compromised by the unknown model behavior under the specific perturbations used. This paper investigates the relationship between uncertainty calibration - the alignment of model confidence with actual accuracy - and perturbation-based explanations. We show that models frequently produce unreliable probability estimates when subjected to explainability-specific perturbations and theoretically prove that this directly undermines explanation quality. To address this, we introduce ReCalX, a novel approach to recalibrate models for improved perturbation-based explanations while preserving their original predictions. Experiments on popular computer vision models demonstrate that our calibration strategy produces explanations that are more aligned with human perception and actual object locations.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。