Prototypical Clustering Networks for Dermatological Disease Diagnosis
It aims to aid doctors in diagnosing dermatological conditions, but the approach appears incremental as it builds on existing Prototypical Networks.
The paper tackles the problem of image classification for dermatological disease diagnosis by addressing long-tailed data distributions and large intra-class variability, proposing Prototypical Clustering Networks (PCN) that extend Prototypical Networks to learn multiple prototypes per class and achieve effective diagnosis on a realistic dataset.
We consider the problem of image classification for the purpose of aiding doctors in dermatological diagnosis. Dermatological diagnosis poses two major challenges for standard off-the-shelf techniques: First, the data distribution is typically extremely long tailed. Second, intra-class variability is often large. To address the first issue, we formulate the problem as low-shot learning, where once deployed, a base classifier must rapidly generalize to diagnose novel conditions given very few labeled examples. To model diverse classes effectively, we propose Prototypical Clustering Networks (PCN), an extension to Prototypical Networks that learns a mixture of prototypes for each class. Prototypes are initialized for each class via clustering and refined via an online update scheme. Classification is performed by measuring similarity to a weighted combination of prototypes within a class, where the weights are the inferred cluster responsibilities. We demonstrate the strengths of our approach in effective diagnosis on a realistic dataset of dermatological conditions.