'Less Than One'-Shot Learning: Learning N Classes From M<N Samples

09/17/2020
by   Ilia Sucholutsky, et al.
1

Deep neural networks require large training sets but suffer from high computational cost and long training times. Training on much smaller training sets while maintaining nearly the same accuracy would be very beneficial. In the few-shot learning setting, a model must learn a new class given only a small number of samples from that class. One-shot learning is an extreme form of few-shot learning where the model must learn a new class from a single example. We propose the `less than one'-shot learning task where models must learn N new classes given only M<N examples and we show that this is achievable with the help of soft labels. We use a soft-label generalization of the k-Nearest Neighbors classifier to explore the intricate decision landscapes that can be created in the `less than one'-shot learning setting. We analyze these decision landscapes to derive theoretical lower bounds for separating N classes using M<N soft-label samples and investigate the robustness of the resulting systems.

READ FULL TEXT

page 4

page 6

page 7

research
11/16/2017

Learning to Compare: Relation Network for Few-Shot Learning

We present a conceptually simple, flexible, and general framework for fe...
research
10/31/2022

Learning New Tasks from a Few Examples with Soft-Label Prototypes

It has been experimentally demonstrated that humans are able to learn in...
research
04/28/2022

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

Learning a new concept from one example is a superior function of human ...
research
11/08/2018

Few-shot learning with attention-based sequence-to-sequence models

End-to-end approaches have recently become popular as a means of simplif...
research
02/15/2021

One Line To Rule Them All: Generating LO-Shot Soft-Label Prototypes

Increasingly large datasets are rapidly driving up the computational cos...
research
06/23/2018

Dynamic Spectrum Matching with One-shot Learning

Convolutional neural networks (CNN) have been shown to provide a good so...
research
04/12/2022

Few-shot Learning with Noisy Labels

Few-shot learning (FSL) methods typically assume clean support sets with...

Please sign up or login with your details

Forgot password? Click here to reset