5 - Seminar Meta Learning (SemMeL) - Nicolas Krieg - Meta Dataset - A Dataset of Datasets for Meta Learning/ClipID:25234 previous clip next clip

Keywords: meta learning
Recording date 2020-11-30

Language

English

Organisational Unit

Friedrich-Alexander-Universität Erlangen-Nürnberg

Producer

Friedrich-Alexander-Universität Erlangen-Nürnberg

Today Nicolas presents "Meta Dataset - A Dataset of Datasets for Meta Learning".

Abstract: Few-shot classification refers to learning a classifier for new classes given only a few examples. While a plethora of models have emerged to tackle it, we find the procedure and datasets that are used to assess their progress lacking. To address this limitation, we propose Meta-Dataset: a new benchmark for training and evaluating models that is large-scale, consists of diverse datasets, and presents more realistic tasks. We experiment with popular baselines and meta-learners on Meta-Dataset, along with a competitive method that we propose. We analyze performance as a function of various characteristics of test tasks and examine the models' ability to leverage diverse training sources for improving their generalization. We also propose a new set of baselines for quantifying the benefit of meta-learning in Meta-Dataset. Our extensive experimentation has uncovered important research challenges and we hope to inspire work in these directions.

https://arxiv.org/abs/1903.03096

 

More clips in this category "Friedrich-Alexander-Universität Erlangen-Nürnberg"

2024-02-06
Studon
protected  
2024-02-06
Passwort / Studon
protected  
2024-02-05
IdM-login
protected