Our new X account is live! Follow @wizwand_team for updates
WorkDL logo mark

Deep Meta-Learning: Learning to Learn in the Concept Space

About

Few-shot learning remains challenging for meta-learning that learns a learning algorithm (meta-learner) from many related tasks. In this work, we argue that this is due to the lack of a good representation for meta-learning, and propose deep meta-learning to integrate the representation power of deep learning into meta-learning. The framework is composed of three modules, a concept generator, a meta-learner, and a concept discriminator, which are learned jointly. The concept generator, e.g. a deep residual net, extracts a representation for each instance that captures its high-level concept, on which the meta-learner performs few-shot learning, and the concept discriminator recognizes the concepts. By learning to learn in the concept space rather than in the complicated instance space, deep meta-learning can substantially improve vanilla meta-learning, which is demonstrated on various few-shot image recognition problems. For example, on 5-way-1-shot image recognition on CIFAR-100 and CUB-200, it improves Matching Nets from 50.53% and 56.53% to 58.18% and 63.47%, improves MAML from 49.28% and 50.45% to 56.65% and 64.63%, and improves Meta-SGD from 53.83% and 53.34% to 61.62% and 66.95%, respectively.

Fengwei Zhou, Bin Wu, Zhenguo Li• 2018

Related benchmarks

TaskDatasetResultRank
Few-shot Image ClassificationMini-Imagenet (test)
Accuracy71.3
235
5-way ClassificationminiImageNet (test)--
231
Few-shot classificationCUB (test)
Accuracy77.1
145
5-way Few-shot ClassificationCUB
5-shot Acc77.1
95
5-way Few-shot ClassificationCIFAR100
1-shot Acc61.6
6
5-way Few-shot ClassificationCaltech-256
1-shot Accuracy62.2
6
Showing 6 of 6 rows

Other info

Follow for update