面向ResNet的具备守恒性的逐层相关性传播（Layer-Wise Relevance Propagation）
Layer-Wise Relevance Propagation with Conservation Property for ResNet
AI总结：
针对传统LRP未充分考虑跳跃连接、难以适配ResNet的问题，研究提出带相关性拆分的守恒性LRP方法，在ImageNet等数据集上的插入-删除分数等指标优于基线，将开源代码。
摘要：
解释方法的透明公式化对于阐明通常为黑盒模型的神经网络预测至关重要。逐层相关性传播（LRP）是一种成熟的方法，它通过反向传播相关性分数，透明地追溯模型预测在其架构中的反向流动过程。然而，传统的LRP并未充分考虑跳跃连接的存在，因此其在广泛使用的ResNet架构上的应用尚未得到深入探究。在本研究中，我们通过在跳跃连接的输出与残差块的输出汇合的位置引入相关性拆分，将LRP扩展到ResNet模型。我们的公式在整个过程中保证了守恒性，从而保留了生成解释的完整性。为了评估我们方法的有效性，我们在ImageNet和Caltech-UCSD Birds-200-2011数据集上开展了实验。我们的方法在插入-删除分数等标准评估指标上取得了优于基线方法的性能，同时保持了其守恒性。我们将在https://5ei74r0.github.io/lrp-for-resnet.page/发布代码以供进一步研究。
英文摘要：
The transparent formulation of explanation methods is essential for elucidating the predictions of neural networks, which are typically black-box models. Layer-wise Relevance Propagation (LRP) is a well-established method that transparently traces the flow of a model's prediction backward through its architecture by backpropagating relevance scores. However, the conventional LRP does not fully consider the existence of skip connections, and thus its application to the widely used ResNet architecture has not been thoroughly explored. In this study, we extend LRP to ResNet models by introducing Relevance Splitting at points where the output from a skip connection converges with that from a residual block. Our formulation guarantees the conservation property throughout the process, thereby preserving the integrity of the generated explanations. To evaluate the effectiveness of our approach, we conduct experiments on ImageNet and the Caltech-UCSD Birds-200-2011 dataset. Our method achieves superior performance to that of baseline methods on standard evaluation metrics such as the Insertion-Deletion score while maintaining its conservation property. We will release our code for further research at https://5ei74r0.github.io/lrp-for-resnet.page/
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。
