Discriminative k-shot learning using probabilistic models
This addresses the problem of few-shot learning for AI systems needing to adapt to new classes with limited data, representing an incremental improvement over existing methods.
The paper tackles k-shot image classification by introducing a probabilistic framework that combines representational and concept transfer, achieving state-of-the-art results on a standard dataset by a large margin and providing well-calibrated uncertainty estimates.
This paper introduces a probabilistic framework for k-shot image classification. The goal is to generalise from an initial large-scale classification task to a separate task comprising new classes and small numbers of examples. The new approach not only leverages the feature-based representation learned by a neural network from the initial task (representational transfer), but also information about the classes (concept transfer). The concept information is encapsulated in a probabilistic model for the final layer weights of the neural network which acts as a prior for probabilistic k-shot learning. We show that even a simple probabilistic model achieves state-of-the-art on a standard k-shot learning dataset by a large margin. Moreover, it is able to accurately model uncertainty, leading to well calibrated classifiers, and is easily extensible and flexible, unlike many recent approaches to k-shot learning.