How to Train Your MAML to Excel in Few-Shot Classification

• URL: http://arxiv.org/abs/2106.16245v1
• Date: Wed, 30 Jun 2021 17:56:15 GMT
• Title: How to Train Your MAML to Excel in Few-Shot Classification
• Authors: Han-Jia Ye, Wei-Lun Chao
• Abstract summary: We show how to train MAML to excel in few-shot classification. Our approach, which we name UNICORN-MAML, performs on a par with or even outperforms state-of-the-art algorithms.
• Score: 26.51244463209443
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Model-agnostic meta-learning (MAML) is arguably the most popular meta-learning algorithm nowadays, given its flexibility to incorporate various model architectures and to be applied to different problems. Nevertheless, its performance on few-shot classification is far behind many recent algorithms dedicated to the problem. In this paper, we point out several key facets of how to train MAML to excel in few-shot classification. First, we find that a large number of gradient steps are needed for the inner loop update, which contradicts the common usage of MAML for few-shot classification. Second, we find that MAML is sensitive to the permutation of class assignments in meta-testing: for a few-shot task of $N$ classes, there are exponentially many ways to assign the learned initialization of the $N$-way classifier to the $N$ classes, leading to an unavoidably huge variance. Third, we investigate several ways for permutation invariance and find that learning a shared classifier initialization for all the classes performs the best. On benchmark datasets such as MiniImageNet and TieredImageNet, our approach, which we name UNICORN-MAML, performs on a par with or even outperforms state-of-the-art algorithms, while keeping the simplicity of MAML without adding any extra sub-networks.

Related papers

• Many or Few Samples? Comparing Transfer, Contrastive and Meta-Learning in Encrypted Traffic Classification [68.19713459228369]
  We compare transfer learning, meta-learning and contrastive learning against reference Machine Learning (ML) tree-based and monolithic DL models. We show that (i) using large datasets we can obtain more general representations, (ii) contrastive learning is the best methodology. While ML tree-based cannot handle large tasks but fits well small tasks, by means of reusing learned representations, DL methods are reaching tree-based models performance also for small tasks.
  arXiv  Detail & Related papers  (2023-05-21T11:20:49Z)
• Few-Shot Class-Incremental Learning by Sampling Multi-Phase Tasks [59.12108527904171]
  A model should recognize new classes and maintain discriminability over old classes. The task of recognizing few-shot new classes without forgetting old classes is called few-shot class-incremental learning (FSCIL) We propose a new paradigm for FSCIL based on meta-learning by LearnIng Multi-phase Incremental Tasks (LIMIT)
  arXiv  Detail & Related papers  (2022-03-31T13:46:41Z)
• Model-Agnostic Multitask Fine-tuning for Few-shot Vision-Language Transfer Learning [59.38343286807997]
  We propose Model-Agnostic Multitask Fine-tuning (MAMF) for vision-language models on unseen tasks. Compared with model-agnostic meta-learning (MAML), MAMF discards the bi-level optimization and uses only first-order gradients. We show that MAMF consistently outperforms the classical fine-tuning method for few-shot transfer learning on five benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-09T17:26:53Z)
• Memory-Based Optimization Methods for Model-Agnostic Meta-Learning and Personalized Federated Learning [56.17603785248675]
  Model-agnostic meta-learning (MAML) has become a popular research area. Existing MAML algorithms rely on the episode' idea by sampling a few tasks and data points to update the meta-model at each iteration. This paper proposes memory-based algorithms for MAML that converge with vanishing error.
  arXiv  Detail & Related papers  (2021-06-09T08:47:58Z)
• Repurposing Pretrained Models for Robust Out-of-domain Few-Shot Learning [23.135033752967598]
  We consider the novel problem of repurposing pretrained MAML checkpoints to solve new few-shot classification tasks. Because of the potential distribution mismatch, the original MAML steps may no longer be optimal. We propose an alternative metatesting procedure and combine adversarial training and uncertainty-based stepsize adaptation.
  arXiv  Detail & Related papers  (2021-03-16T12:53:09Z)
• A Nested Bi-level Optimization Framework for Robust Few Shot Learning [10.147225934340877]
  NestedMAML learns to assign weights to training tasks or instances. Experiments on synthetic and real-world datasets demonstrate that NestedMAML efficiently mitigates the effects of "unwanted" tasks or instances.
  arXiv  Detail & Related papers  (2020-11-13T06:41:22Z)
• MetaMix: Improved Meta-Learning with Interpolation-based Consistency Regularization [14.531741503372764]
  We propose an approach called MetaMix to regularize backbone models. It generates virtual feature-target pairs within each episode to regularize the backbone models. It can be integrated with any of the MAML-based algorithms and learn the decision boundaries generalizing better to new tasks.
  arXiv  Detail & Related papers  (2020-09-29T02:44:13Z)
• Many-Class Few-Shot Learning on Multi-Granularity Class Hierarchy [57.68486382473194]
  We study many-class few-shot (MCFS) problem in both supervised learning and meta-learning settings. In this paper, we leverage the class hierarchy as a prior knowledge to train a coarse-to-fine classifier. The model, "memory-augmented hierarchical-classification network (MahiNet)", performs coarse-to-fine classification where each coarse class can cover multiple fine classes.
  arXiv  Detail & Related papers  (2020-06-28T01:11:34Z)
• Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need? [72.00712736992618]
  We show that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, outperforms state-of-the-art few-shot learning methods. An additional boost can be achieved through the use of self-distillation. We believe that our findings motivate a rethinking of few-shot image classification benchmarks and the associated role of meta-learning algorithms.
  arXiv  Detail & Related papers  (2020-03-25T17:58:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.