SimLoss: Class Similarities in Cross Entropy
This addresses the issue of incorporating class structure in classification tasks for machine learning practitioners, though it is incremental as it modifies an existing loss function.
The paper tackles the problem of Categorical Cross Entropy (CCE) treating all misclassifications equally by introducing SimLoss, a drop-in replacement that incorporates class similarities, resulting in significant improvements over CCE on Age Estimation and Image Classification tasks.
One common loss function in neural network classification tasks is Categorical Cross Entropy (CCE), which punishes all misclassifications equally. However, classes often have an inherent structure. For instance, classifying an image of a rose as "violet" is better than as "truck". We introduce SimLoss, a drop-in replacement for CCE that incorporates class similarities along with two techniques to construct such matrices from task-specific knowledge. We test SimLoss on Age Estimation and Image Classification and find that it brings significant improvements over CCE on several metrics. SimLoss therefore allows for explicit modeling of background knowledge by simply exchanging the loss function, while keeping the neural network architecture the same. Code and additional resources can be found at https://github.com/konstantinkobs/SimLoss.