A simple squared-error reformulation for ordinal classification
This work addresses ordinal classification, a common problem in domains like medical imaging, with an incremental improvement over existing methods.
The paper tackled ordinal classification in deep neural networks by reformulating squared error loss to respect class ordering and produce discrete probability distributions, achieving superior performance on the Kaggle diabetic retinopathy dataset compared to baselines.
In this paper, we explore ordinal classification (in the context of deep neural networks) through a simple modification of the squared error loss which not only allows it to not only be sensitive to class ordering, but also allows the possibility of having a discrete probability distribution over the classes. Our formulation is based on the use of a softmax hidden layer, which has received relatively little attention in the literature. We empirically evaluate its performance on the Kaggle diabetic retinopathy dataset, an ordinal and high-resolution dataset and show that it outperforms all of the baselines employed.