C3-LRP: Visual Explanation Generation based on Layer-Wise Relevance Propagation for ResNet

We introduce a novel calculation method for Layer- wise Relevance Propagation (LRP) specifically tailored to models featuring skip connections such as ResNet. This method’s strength lies in its adaptability, as the backpropagation technique is distinctly defined for each layer, enhancing its extensibility. To validate our method, we conduct an experiment on the CUB-200-2011 dataset. The proposed method successfully generates appropriate explanations and, based on the Insertion-Deletion score, outperforms the baseline methods.

Paper link: Click here

Recommended citation: Félix DOUBLET, Seitaro OTSUKI, Iida TSUMUGI, and Komei SUGIURA. "C3-LRP: Visual Explanation Generation based on Layer-Wise Relevance Propagation for ResNet." 人工知能学会全国大会論文集, vol. JSAI2024, pp. 4Q1IS2c03-4Q1IS2c03, 2024. https://www.jstage.jst.go.jp/article/pjsai/JSAI2024/0/JSAI2024_4Q1IS2c03/_pdf/-char/ja