Abstract
We propose a new framework for prototypical learning that bases decision-making on few relevant examples that we call prototypes. Our framework utilizes an attention mechanism that relates the encoded representations to determine the prototypes. This results in a model that: (1) enables interpretability by outputting samples most relevant to the decision-making in addition to outputting the classification results; (2) allows confidence-controlled prediction by quantifying the mismatch across prototype labels; (3) permits detection of distribution mismatch; and (4) improves robustness to label noise. We demonstrate that our model is able to maintain comparable performance to baseline models while enabling all these benefits.
Abstract (translated by Google)
URL
http://arxiv.org/abs/1902.06292