mlsanityData to 7 Oct 2026

PLATINUM: Semi-Supervised Model Agnostic Meta-Learning using Submodular Mutual Information

arXiv 2201.12928 ↗First posted 30 Jan 2022cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

Few-shot classification (FSC) requires training models using a few (typically one to five) data points per class. Meta learning has proven to be able to learn a parametrized model for FSC by training on various other classification tasks. In this work, we propose PLATINUM (semi-suPervised modeL Agnostic meTa-learnIng usiNg sUbmodular Mutual information), a novel semi-supervised model agnostic meta-learning framework that uses the submodular mutual information (SMI) functions to boost the performance of FSC. PLATINUM leverages unlabeled data in the inner and outer loop using SMI functions during meta-training and obtains richer meta-learned parameterizations for meta-test. We study the performance of PLATINUM in two scenarios - 1) where the unlabeled data points belong to the same set of classes as the labeled set of a certain episode, and 2) where there exist out-of-distribution classes that do not belong to the labeled set. We evaluate our method on various settings on the miniImageNet, tieredImageNet and Fewshot-CIFAR100 datasets. Our experiments show that PLATINUM outperforms MAML and semi-supervised approaches like pseduo-labeling for semi-supervised FSC, especially for small ratio of labeled examples per class.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 44 of its 59 references that are in the map. First posted on arXiv 30 Jan 2022.

Builds on

44 of 59 references.

References · 44

  1. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  2. 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
  3. 2017Prototypical Networks for Few-shot Learningcited by 3,001
  4. 2016Matching Networks for One Shot Learningcited by 2,246
  5. 2020FixMatch: Simplifying Semi-Supervised Learning with Consistency and Confidencecited by 2,080
  6. 2019MixMatch: A Holistic Approach to Semi-Supervised Learningcited by 1,390
  7. 2019Unsupervised Data Augmentation for Consistency Trainingcited by 1,057
  8. 2016Temporal Ensembling for Semi-Supervised Learningcited by 1,054
  9. 2017Virtual Adversarial Training: A Regularization Method for Supervised and Semi-Supervised Learningcited by 918
  10. 2019A Closer Look at Few-shot Classificationcited by 679
  11. 2018Meta-Learning with Latent Embedding Optimizationcited by 476
  12. 2017Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning resultscited by 470
32 more
  1. 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
  2. 2016Regularization With Stochastic Transformations and Perturbations for Deep Semi-Supervised Learningcited by 441
  3. 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
  4. 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
  5. 2018Meta-learning with differentiable closed-form solverscited by 395
  6. 2018How to train your MAMLcited by 306
  7. 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
  8. 2017Meta Networkscited by 268
  9. 2018Probabilistic Model-Agnostic Meta-Learningcited by 254
  10. 2020GLISTER: Generalization based Data Subset Selection for Efficient and Robust Learningcited by 224
  11. 2018Learning to Propagate Labels: Transductive Propagation Network for Few-shot Learningcited by 208
  12. 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
  13. 2019On the Convergence Theory of Gradient-Based Model-Agnostic Meta-Learning Algorithmscited by 132
  14. 2014Lazier Than Lazy Greedycited by 97
  15. 2020Submodular Combinatorial Information Measures with Applications in Machine Learningcited by 88
  16. 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
  17. 2021SIMILAR: Submodular Information Measures Based Active Learning In Realistic Scenarioscited by 83
  18. 2019Learning From Less Data: A Unified Data Subset Selection and Active Learning Framework for Computer Visioncited by 64
  19. 2020Instance Credibility Inference for Few-Shot Learningcited by 57
  20. 2021PRISM: A Rich Class of Parameterized Submodular Information Measures for Guided Subset Selectioncited by 50
  21. 2020Iterative label cleaning for transductive and semi-supervised few-shot learningcited by 40
  22. 2019TransMatch: A Transfer-Learning Scheme for Semi-Supervised Few-Shot Learningcited by 39
  23. 2021TALISMAN: Targeted Active Learning for Object Detection with Rare Classes and Slices using Submodular Mutual Informationcited by 27
  24. 2015Submodular Functions: from Discrete to Continous Domainscited by 24
  25. 2020Submodularity in Action: From Machine Learning to Signal Processing Applicationscited by 12
  26. 2021The Role of Global Labels in Few-Shot Classification and How to Infer Themcited by 12
  27. 2020PTN: A Poisson Transfer Network for Semi-supervised Few-shot Learningcited by 9
  28. 2018A Framework towards Domain Specific Video Summarizationcited by 8
  29. 2019A Memoization Framework for Scaling Submodular Optimization to Large Scale Problemscited by 8
  30. 2020Deep Submodular Networks for Extractive Data Summarizationcited by 8
  31. 2020A Nested Bi-level Optimization Framework for Robust Few Shot Learningcited by 7
  32. 2020Realistic Video Summarization through VISIOCITY: A New Benchmark and Evaluation Frameworkcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 1; 2025: 1.

3 papers.

  1. 2022Pseudo-Labeling Based Practical Semi-Supervised Meta-Training for Few-Shot Learningcited by 4
  2. 2025Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detectioncited by 4
  3. 2024Theoretical Analysis of Submodular Information Measures for Targeted Data Subset Selectioncited by 1