Few-shot learning in deep networks through global prototyping

DOI10.1016/J.NEUNET.2017.07.001MaRDI QIDQ2292229zbMATH OpenOpenAlexWikidataFDO

Authors Sebastian Blaes, Thomas T. Burwick

Publication date 3 February 2020

Published in Neural Networks (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.neunet.2017.07.001

zbMATH Keywords

convolutional neural networksdeep learningfew-shot learningobject recognitiontransfer learning

Mathematics Subject Classification ID

Artificial neural networks and deep learning (68T07)

Recommendations

• Few-shot learning
• A survey of few-shot object detection
• Learning adaptive classifiers synthesis for generalized few-shot learning
• Deep learning algorithm with visual impression
• Self-augmentation: generalizing deep networks to unseen classes for few-shot learning

Cites work

• Human-level concept learning through probabilistic program induction
• Visualizing data using t-SNE

Cited in

(7)

• Learning adaptive classifiers synthesis for generalized few-shot learning
• Splicing learning: a novel few-shot learning approach
• Few-shot learning
• ProtoAttend: Attention-Based Prototypical Learning
• Self-augmentation: generalizing deep networks to unseen classes for few-shot learning
• A geometric view on the role of nonlinear feature maps in few-shot learning
• Are LSTMs good few-shot learners?

Describes a project that uses

Uses Software

• ImageNet
• AlexNet
• WordNet
• Omniglot
• t-SNE

This page was built for publication: Few-shot learning in deep networks through global prototyping

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2292229)