Bayesian Embeddings for Few-Shot Open World Recognition

07/29/2021
by   John Willes, et al.
8

As autonomous decision-making agents move from narrow operating environments to unstructured worlds, learning systems must move from a closed-world formulation to an open-world and few-shot setting in which agents continuously learn new classes from small amounts of information. This stands in stark contrast to modern machine learning systems that are typically designed with a known set of classes and a large number of examples for each class. In this work we extend embedding-based few-shot learning algorithms to the open-world recognition setting. We combine Bayesian non-parametric class priors with an embedding-based pre-training scheme to yield a highly flexible framework which we refer to as few-shot learning for open world recognition (FLOWR). We benchmark our framework on open-world extensions of the common MiniImageNet and TieredImageNet few-shot learning datasets. Our results show, compared to prior methods, strong classification accuracy performance and up to a 12 in H-measure (a measure of novel class detection) from our non-parametric open-world few-shot learning scheme.

READ FULL TEXT

page 4

page 12

research
12/24/2020

Task-Adaptive Negative Class Envision for Few-Shot Open-Set Recognition

Recent works seek to endow recognition systems with the ability to handl...
research
08/22/2017

Dynamic Input Structure and Network Assembly for Few-Shot Learning

The ability to learn from a small number of examples has been a difficul...
research
06/23/2020

Discrete Few-Shot Learning for Pan Privacy

In this paper we present the first baseline results for the task of few-...
research
08/26/2019

Bayesian Nonparametrics for Non-exhaustive Learning

Non-exhaustive learning (NEL) is an emerging machine-learning paradigm d...
research
01/20/2023

Open-Set Likelihood Maximization for Few-Shot Learning

We tackle the Few-Shot Open-Set Recognition (FSOSR) problem, i.e. classi...
research
05/01/2021

One-shot learning for acoustic identification of bird species in non-stationary environments

This work introduces the one-shot learning paradigm in the computational...
research
07/06/2020

In the Wild: From ML Models to Pragmatic ML Systems

Enabling robust intelligence in the wild entails learning systems that o...

Please sign up or login with your details

Forgot password? Click here to reset