PiPS：用于可解释语义分割的事后原型解释
PiPS: Post-Hoc Prototypical Explanations for Interpretable Semantic Segmentation
- Jagiellonian University（雅盖隆大学）
- Wrocław University of Science and Technology（弗罗茨瓦夫理工大学）
- IDEAS Research Institute（IDEAS 研究所）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
PiPS提出首个完全事后原型解释方法，无需修改或微调即可为任意预训练语义分割模型生成直观、空间局部化的解释，并保留100%原始预测性能。
AI中文摘要：
随着深度神经网络在医疗诊断和自动驾驶等关键系统中的部署日益增多，确保其可解释性对于建立对决策系统的信任至关重要。在可解释人工智能领域，基于原型的推理因其通过“看起来像这样”范式下的视觉相似性来解释模型决策，模拟了人类的认知过程而广受欢迎。虽然这一范式已在全局图像分类背景下得到深入研究，但密集预测（特别是语义分割）的可解释性在很大程度上仍未得到探索，尽管其在需要精确目标定位的任务中具有极其重要的意义。现有的基于原型的可解释分割模型依赖于事前架构，这带来了显著的限制，因为它们需要昂贵的从头训练和对网络结构的修改，最终导致与标准黑盒模型相比预测性能明显下降。为解决这一问题，我们提出了PiPS（事后可解释原型分割），这是首个完全事后解决方案，用于为语义分割模型生成原型解释。我们的方法能够从任何预训练网络中提取直观的、空间局部化的解释，而无需修改或微调，从而保留了模型原始预测性能的100%。这种方法为在高级计算机视觉任务中安全且经济高效地部署透明系统开辟了新途径。代码库可在https://this https URL获取。
英文摘要：
With the increasing deployment of deep neural networks in critical systems, such as medical diagnostics and autonomous vehicles, ensuring their interpretability is crucial to building trust in decision-making systems. In the field of explainable artificial intelligence, prototype-based reasoning has gained particular popularity, as it mimics human cognitive processes by explaining model decisions based on visual similarity under the looks like this paradigm. While this paradigm has been thoroughly investigated in the context of global image classification, the interpretability of dense predictions, particularly semantic segmentation, remains largely unexplored despite its immense importance in tasks requiring precise object localization. Existing prototype-based interpretable segmentation models rely on ante-hoc architectures, which entails significant limitations because they require costly training from scratch and modifications to the network structure, ultimately leading to a noticeable drop in predictive performance compared to standard black-box models. To address this issue, we propose PiPS (Post-hoc interpretable Prototypical Segmentation), the first fully post-hoc solution for generating prototypical explanations for semantic segmentation models. Our method enables the extraction of intuitive, spatially localized explanations from any pre-trained network without modification or fine-tuning, thereby preserving 100% of the model's original predictive performance. This approach opens a new avenue for the safe and cost-effective deployment of transparent systems in advanced computer vision tasks. Codebase available at https://github.com/gmum/PIPS.
