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/

翻译：解释方法的透明表述对于阐明神经网络（通常为黑盒模型）的预测机制至关重要。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，透明地追踪模型预测在架构中的逆向流动。然而，传统LRP未能充分考虑跳跃连接的存在，因此其在广泛使用的ResNet架构中的应用尚未得到深入探索。本研究通过引入相关性分割机制，将LRP扩展至ResNet模型——该机制在跳跃连接输出与残差块输出汇聚处实施分割操作。我们的公式化方法保证了整个过程中的守恒特性，从而确保生成解释的完整性。为评估所提方法的有效性，我们在ImageNet和Caltech-UCSD Birds-200-2011数据集上进行了实验。在保持守恒特性的同时，我们的方法在插入-删除分数等标准评估指标上均优于基线方法。我们将通过https://5ei74r0.github.io/lrp-for-resnet.page/ 发布代码以供后续研究。