Discriminative k-shot learning using probabilistic models

by   Matthias Bauer, et al.

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.


page 1

page 2

page 3

page 4


Metalearning with Hebbian Fast Weights

We unify recent neural approaches to one-shot learning with older ideas ...

Large Margin Few-Shot Learning

The key issue of few-shot learning is learning to generalize. In this pa...

It's DONE: Direct ONE-shot learning without training optimization

Learning a new concept from one example is a superior function of human ...

Low-shot learning with large-scale diffusion

This paper considers the problem of inferring image labels for which onl...

Generating Classification Weights with GNN Denoising Autoencoders for Few-Shot Learning

Given an initial recognition model already trained on a set of base clas...

Uncertainty in Multitask Transfer Learning

Using variational Bayes neural networks, we develop an algorithm capable...

On the Role of Neural Collapse in Transfer Learning

We study the ability of foundation models to learn representations for c...