Reproducibility review of "Why Not Other Classes": Towards Class-Contrastive Back-Propagation Explanations
This work addresses reproducibility and generalization challenges for researchers in explainable AI, but it is incremental as it builds on existing methods.
The authors reproduced a method for class-contrastive explanations in neural network image classifiers, showing similar results but with visualization differences, and extended it to other methods and Vision Transformers, finding good generalization while identifying issues like lack of detail and an erroneous equation in the original paper.
"Why Not Other Classes?": Towards Class-Contrastive Back-Propagation Explanations (Wang & Wang, 2022) provides a method for contrastively explaining why a certain class in a neural network image classifier is chosen above others. This method consists of using back-propagation-based explanation methods from after the softmax layer rather than before. Our work consists of reproducing the work in the original paper. We also provide extensions to the paper by evaluating the method on XGradCAM, FullGrad, and Vision Transformers to evaluate its generalization capabilities. The reproductions show similar results as the original paper, with the only difference being the visualization of heatmaps which could not be reproduced to look similar. The generalization seems to be generally good, with implementations working for Vision Transformers and alternative back-propagation methods. We also show that the original paper suffers from issues such as a lack of detail in the method and an erroneous equation which makes reproducibility difficult. To remedy this we provide an open-source repository containing all code used for this project.