基于概念的解释与类对比
Concept Based Explanations and Class Contrasting
AI总结：
本文提出一种基于概念的解释方法，用于解释深度神经网络的单类预测及两类对比，并在ImageNet1K模型上验证了其定性与定量有效性。
摘要：
解释深度神经网络具有挑战性，因为其规模庞大且具有非线性。本文引入一种基于概念的解释方法，用于解释单个类别的预测，并对比任意两个类别，即解释为何模型预测某一类而非另一类。我们在多个基于ImageNet1K训练的公开分类模型上进行了测试。我们进行了定性和定量测试。例如，对于pytorch model zoo中的ResNet50模型，我们可以利用对模型预测类别'A'的解释，自动选择四个模型未预测为类别'A'的数据集裁剪图像。随后，对于新组合的图像，模型在91.1%的情况下（在1000个类别中的911个）再次预测为类别'A'。包含.ipynb示例的代码可在github获取：https://github.com/rherdt185/concept-based-explanations-and-class-contrasting
英文摘要：
Explaining deep neural networks is challenging, due to their large size and non-linearity. In this paper, we introduce a concept-based explanation method, in order to explain the prediction for an individual class, as well as contrasting any two classes, i.e. explain why the model predicts one class over the other. We test it on several openly available classification models trained on ImageNet1K. We perform both qualitative and quantitative tests. For example, for a ResNet50 model from pytorch model zoo, we can use the explanation for why the model predicts a class 'A' to automatically select four dataset crops where the model does not predict class 'A'. The model then predicts class 'A' again for the newly combined image in 91.1% of the cases (works for 911 out of the 1000 classes). The code including an .ipynb example is available on github: https://github.com/rherdt185/concept-based-explanations-and-class-contrasting
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。
