Predefined Prototypes for Intra-Class Separation and Disentanglement
This work addresses the challenge of enhancing model interpretability and performance in few-shot or explainable AI scenarios, though it appears incremental by building on existing prototypical learning methods.
The paper tackles the problem of improving inter-class separability and disentangling embeddings in prototypical learning by predefining prototypes based on human-specified criteria, which simplifies training and offers advantages such as explainable predictions, as demonstrated through experiments.
Prototypical Learning is based on the idea that there is a point (which we call prototype) around which the embeddings of a class are clustered. It has shown promising results in scenarios with little labeled data or to design explainable models. Typically, prototypes are either defined as the average of the embeddings of a class or are designed to be trainable. In this work, we propose to predefine prototypes following human-specified criteria, which simplify the training pipeline and brings different advantages. Specifically, in this work we explore two of these advantages: increasing the inter-class separability of embeddings and disentangling embeddings with respect to different variance factors, which can translate into the possibility of having explainable predictions. Finally, we propose different experiments that help to understand our proposal and demonstrate empirically the mentioned advantages.