无需原始数据，用生成模型直接合成解释图像的原型。
ProDG: Prototypes for Data-Free Generative Post-Hoc Explainability
- 用生成模型从冻结模型权重中直接合成视觉原型。
- 无需任何外部数据即可实现对单张图像的准确解释。
- 适合隐私敏感场景，如医疗影像、金融风控等。
基于原型的前向可解释方法通过直观的‘这看起来像那’推理机制提供高精度解释。而后向解释模型可在不依赖底层数据或昂贵重训练的情况下解释单张图像的预测结果。近期方法虽解决了原型网络的重训练问题，但仍需访问部分数据（如测试集或验证集）以搜索和提取视觉原型。本文提出ProDG：无数据后向可解释的生成原型框架，利用生成模型直接从冻结模型的权重中合成纯净、高保真原型，完全消除对外部数据的依赖。该方法开创了无数据XAI新范式，为原始数据严格受限或根本不可获取的隐私敏感领域（如医疗影像）提供了稳健的视觉可解释性支持。项目主页：https://github.com/piotr310100/ProDG
原文摘要 · Abstract (English)
Ante-hoc interpretability methods based on prototypes provide highly accurate explanations by utilizing the intuitive "this looks like that" reasoning paradigm. On the other hand, post-hoc models can explain predictions for a single image without relying on an underlying dataset or requiring costly neural network retraining. Recent approaches successfully solve the retraining problem for prototype-based networks. However, they still face a fundamental limitation: they require access to a subset of data (e.g., a test or validation set) to search for and extract the visual prototypes. In this paper, we address this issue and introduce ProDG: Generative Prototypes for Data-Free Post-Hoc Explainability, a novel framework that leverages generative models to synthesize pure, high-fidelity prototypes directly from the frozen model's weights, completely eliminating the dependency on any external data. By establishing this new frontier in Data-Free XAI, ProDG unlocks robust visual interpretability for privacy-sensitive domains, where original data is strictly restricted or fundamentally inaccessible. Project page: https://github.com/piotr310100/ProDG
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。