Discriminative k-shot learning using probabilistic models

Matthias Bauer, Mateo Rojas-Carulla, Jakub Bartłomiej Świątkowski, Bernhard Schölkopf, Richard E. Turner

Abstract: 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.

TL;DR: This paper introduces a probabilistic framework for k-shot image classification that achieves state-of-the-art results

Keywords: discriminative k-shot learning, probabilistic inference

Data: [mini-Imagenet](https://paperswithcode.com/dataset/mini-imagenet)

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/discriminative-k-shot-learning-using/code)