mlsanityData to 7 Oct 2026

Transfer learning based few-shot classification using optimal transport mapping from preprocessed latent space of backbone neural network

arXiv 2102.05176 ↗First posted 9 Feb 2021cs.LG cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

MetaDL Challenge 2020 focused on image classification tasks in few-shot settings. This paper describes second best submission in the competition. Our meta learning approach modifies the distribution of classes in a latent space produced by a backbone network for each class in order to better follow the Gaussian distribution. After this operation which we call Latent Space Transform algorithm, centers of classes are further aligned in an iterative fashion of the Expectation Maximisation algorithm to utilize information in unlabeled data that are often provided on top of few labelled instances. For this task, we utilize optimal transport mapping using the Sinkhorn algorithm. Our experiments show that this approach outperforms previous works as well as other variants of the algorithm, using K-Nearest Neighbour algorithm, Gaussian Mixture Models, etc.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 12 of its 21 references that are in the map. First posted on arXiv 9 Feb 2021.

Builds on

12 of 21 references.

References · 12

  1. 2016Wide Residual Networkscited by 3,057
  2. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  3. 2013Sinkhorn Distances: Lightspeed Computation of Optimal Transportation Distancescited by 2,277
  4. 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
  5. 2019Generalizing from a Few Examples: A Survey on Few-Shot Learningcited by 462
  6. 2018Meta-learning with differentiable closed-form solverscited by 395
  7. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  8. 2019SimpleShot: Revisiting Nearest-Neighbor Classification for Few-Shot Learningcited by 194
  9. 2019Charting the Right Manifold: Manifold Mixup for Few-shot Learningcited by 135
  10. 2020Leveraging the Feature Distribution in Transfer-based Few-Shot Learningcited by 72
  11. 2019TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learningcited by 39
  12. 2018Adapted Deep Embeddings: A Synthesis of Methods for k-Shot Inductive Transfer Learningcited by 17

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 2.

6 papers.

  1. 2021Squeezing Backbone Feature Distributions to the Max for Efficient Few-Shot Learningcited by 14
  2. 2022Advances in MetaDL: AAAI 2021 challenge and workshopcited by 4
  3. 2022A Statistical Model for Predicting Generalization in Few-Shot Classificationcited by 2
  4. 2022Unidirectional Thin Adapter for Efficient Adaptation of Deep Neural Networkscited by 0
  5. 2023Few-shot Image Classification based on Gradual Machine Learningcited by 0
  6. 2023Using Skew to Assess the Quality of GAN-generated Image Featurescited by 0