Skip to main content

Research Repository

Advanced Search

L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout

Song, Heda; Torres Torres, Mercedes; �zcan, Ender; Triguero, Isaac

L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout Thumbnail


Heda Song

Mercedes Torres Torres

Profile Image

Professor of Computer Science and Operational Research


Few-shot learning focuses on learning a new visual concept with very limited labelled examples. A successful approach to tackle this problem is to compare the similarity between examples in a learned metric space based on convolutional neural networks. However, existing methods typically suffer from meta-level overfitting due to the limited amount of training tasks and do not normally consider the importance of the convolutional features of different examples within the same channel. To address these limitations, we make the following two contributions: (a) We propose a novel meta-learning approach for aggregating useful convolutional features and suppressing noisy ones based on a channel-wise attention mechanism to improve class representations. The proposed model does not require fine-tuning and can be trained in an end-to-end manner. The main novelty lies in incorporating a shared weight generation module that learns to assign different weights to the feature maps of different examples within the same channel. (b) We also introduce a simple meta-level dropout technique that reduces meta-level overfitting in several few-shot learning approaches. In our experiments, we find that this simple technique significantly improves the performance of the proposed method as well as various state-of-the-art meta-learning algorithms. Applying our method to few-shot image recognition using Omniglot and miniImageNet datasets shows that it is capable of delivering a state-of-the-art classification performance.

Journal Article Type Article
Acceptance Date Feb 5, 2021
Online Publication Date Mar 2, 2021
Publication Date Jun 28, 2021
Deposit Date Apr 16, 2021
Publicly Available Date Mar 3, 2023
Journal Neurocomputing
Print ISSN 0925-2312
Publisher Elsevier
Peer Reviewed Peer Reviewed
Volume 442
Pages 200-208
Keywords Cognitive Neuroscience; Artificial Intelligence; Computer Science Applications
Public URL
Publisher URL
Additional Information This article is maintained by: Elsevier; Article Title: L2AE-D: Learning to Aggregate Embeddings for Few-shot Learning with Meta-level Dropout; Journal Title: Neurocomputing; CrossRef DOI link to publisher maintained version:; Content Type: article; Copyright: © 2021 Elsevier B.V. All rights reserved.


You might also like

Downloadable Citations