mlsanityData to 7 Oct 2026

Advances in MetaDL: AAAI 2021 challenge and workshop

arXiv 2202.01890 ↗First posted 1 Feb 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

To stimulate advances in metalearning using deep learning techniques (MetaDL), we organized in 2021 a challenge and an associated workshop. This paper presents the design of the challenge and its results, and summarizes presentations made at the workshop. The challenge focused on few-shot learning classification tasks of small images. Participants' code submissions were run in a uniform manner, under tight computational constraints. This put pressure on solution designs to use existing architecture backbones and/or pre-trained networks. Winning methods featured various classifiers trained on top of the second last layer of popular CNN backbones, fined-tuned on the meta-training data (not necessarily in an episodic manner), then trained on the labeled support and tested on the unlabeled query sets of the meta-test data.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 26 of its 43 references that are in the map. First posted on arXiv 1 Feb 2022.

Builds on

26 of 43 references.

References · 26

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  4. 2017MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applicationscited by 3,827
  5. 2016Wide Residual Networkscited by 3,057
  6. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  7. 2016Matching Networks for One Shot Learningcited by 2,246
  8. 2020Meta-Learning in Neural Networks: A Surveycited by 944
  9. 2016Learning to learn by gradient descent by gradient descentcited by 616
  10. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  11. 2019Meta-Dataset: A Dataset of Datasets for Learning to Learn from Few Examplescited by 312
  12. 2017Meta Networkscited by 268
14 more
  1. 2018Meta-Learning: A Surveycited by 254
  2. 2020CrossTransformers: spatially-aware few-shot transfercited by 174
  3. 2020A Survey of Deep Meta-Learningcited by 99
  4. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 72
  5. 2022Winning solutions and post-challenge analyses of the ChaLearn AutoDL challenge 2019cited by 16
  6. 2021Few-Shot Learning for Road Object Detectioncited by 13
  7. 2018The Algorithm Selection Competitions 2015 and 2017cited by 11
  8. 2021MetaDelta: A Meta-Learning System for Few-shot Image Classificationcited by 10
  9. 2021Stateless Neural Meta-Learning using Second-Order Gradientscited by 7
  10. 2021Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural networkcited by 6
  11. 2021Learning Abstract Task Representationscited by 3
  12. 2021Learning to Continually Learn Rapidly from Few and Noisy Datacited by 3
  13. 2020Fuzzy Simplicial Networks: A Topology-Inspired Model to Improve Task Generalization in Few-shot Learningcited by 2
  14. 2021Stress Testing of Meta-learning Approaches for Few-shot Learningcited by 2

Built on by

Cited by year

Citing papers per year: 2022: 3; 2023: 1.

4 papers.

  1. 2022Lessons learned from the NeurIPS 2021 MetaDL challenge: Backbone fine-tuning without episodic meta-learning dominates for few-shot learning image classificationcited by 10
  2. 2022NeurIPS'22 Cross-Domain MetaDL competition: Design and baseline resultscited by 3
  3. 2023Contrastive Meta-Learning for Partially Observable Few-Shot Learningcited by 2
  4. 2022Meta-learning from Learning Curves Challenge: Lessons learned from the First Round and Design of the Second Roundcited by 1