为什么看起来在那里？用于图像分类的结构化解释
Why Does It Look There? Structured Explanations for Image Classification
AI总结：
I2X通过结构化解释提升图像分类模型的可解释性和预测准确性。
摘要：
深度学习模型实现了显著的预测性能，但其黑箱性质限制了透明性和可信度。尽管已经提出了许多可解释的人工智能（XAI）方法，但它们主要提供显著性图或概念（即无结构的可解释性）。现有方法往往依赖于辅助模型（例如，GPT、CLIP）来描述模型行为，从而损害了对原始模型的忠实性。我们提出了可解释性到可解释性（I2X）框架，该框架通过在训练过程中使用从事后XAI方法（如GradCAM）提取的原型量化进展，直接从无结构的可解释性构建结构化解释。I2X通过提供训练过程中类内和类间决策的结构化视图来回答“为什么看起来在那里”的问题。在MNIST和CIFAR10上的实验表明，I2X能够揭示各种图像分类模型的原型推理过程。此外，我们证明I2X可以用于改进不同模型架构和数据集的预测：我们可以识别被I2X识别的不确定原型，然后使用针对样本的扰动来微调，最终提高准确性。因此，I2X不仅忠实解释了模型行为，还提供了一种实用的方法来引导优化朝着期望的目标进行。
英文摘要：
Deep learning models achieve remarkable predictive performance, yet their black-box nature limits transparency and trustworthiness. Although numerous explainable artificial intelligence (XAI) methods have been proposed, they primarily provide saliency maps or concepts (i.e., unstructured interpretability). Existing approaches often rely on auxiliary models (\eg, GPT, CLIP) to describe model behavior, thereby compromising faithfulness to the original models. We propose Interpretability to Explainability (I2X), a framework that builds structured explanations directly from unstructured interpretability by quantifying progress at selected checkpoints during training using prototypes extracted from post-hoc XAI methods (e.g., GradCAM). I2X answers the question of "why does it look there" by providing a structured view of both intra- and inter-class decision making during training. Experiments on MNIST and CIFAR10 demonstrate effectiveness of I2X to reveal prototype-based inference process of various image classification models. Moreover, we demonstrate that I2X can be used to improve predictions across different model architectures and datasets: we can identify uncertain prototypes recognized by I2X and then use targeted perturbation of samples that allows fine-tuning to ultimately improve accuracy. Thus, I2X not only faithfully explains model behavior but also provides a practical approach to guide optimization toward desired targets.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
