ClassSim: Similarity between Classes Defined by Misclassification Ratios of Trained Classifiers
This work addresses the challenge of handling similar classes in wild datasets for machine learning practitioners, but it is incremental as it builds on existing methods for class similarity evaluation.
The authors tackled the problem of evaluating similarities between classes in real-world datasets by proposing ClassSim, a similarity metric based on misclassification ratios of trained deep neural networks, and demonstrated through image recognition experiments that it provides better similarities compared to existing methods.
Deep neural networks (DNNs) have achieved exceptional performances in many tasks, particularly, in supervised classification tasks. However, achievements with supervised classification tasks are based on large datasets with well-separated classes. Typically, real-world applications involve wild datasets that include similar classes; thus, evaluating similarities between classes and understanding relations among classes are important. To address this issue, a similarity metric, ClassSim, based on the misclassification ratios of trained DNNs is proposed herein. We conducted image recognition experiments to demonstrate that the proposed method provides better similarities compared with existing methods and is useful for classification problems. Source code including all experimental results is available at https://github.com/karino2/ClassSim/.