Explaining Convolutional Neural Networks using Softmax Gradient Layer-wise Relevance Propagation
It addresses the problem of understanding CNN decisions for researchers and practitioners, but is incremental as it extends prior methods like Deep Taylor Decomposition.
The paper tackled the interpretability of CNNs for multi-class image classification by proposing SGLRP, a visualization method that localizes and attributes input regions contributing to predictions, showing it outperforms existing LRP-based methods.
Convolutional Neural Networks (CNN) have become state-of-the-art in the field of image classification. However, not everything is understood about their inner representations. This paper tackles the interpretability and explainability of the predictions of CNNs for multi-class classification problems. Specifically, we propose a novel visualization method of pixel-wise input attribution called Softmax-Gradient Layer-wise Relevance Propagation (SGLRP). The proposed model is a class discriminate extension to Deep Taylor Decomposition (DTD) using the gradient of softmax to back propagate the relevance of the output probability to the input image. Through qualitative and quantitative analysis, we demonstrate that SGLRP can successfully localize and attribute the regions on input images which contribute to a target object's classification. We show that the proposed method excels at discriminating the target objects class from the other possible objects in the images. We confirm that SGLRP performs better than existing Layer-wise Relevance Propagation (LRP) based methods and can help in the understanding of the decision process of CNNs.