Multi-Level Contrastive Learning for Few-Shot Problems
Not on the map. Why?
Abstract (arXiv)
Contrastive learning is a discriminative approach that aims at grouping similar samples closer and diverse samples far from each other. It it an efficient technique to train an encoder generating distinguishable and informative representations, and it may even increase the encoder's transferability. Most current applications of contrastive learning benefit only a single representation from the last layer of an encoder.In this paper, we propose a multi-level contrasitive learning approach which applies contrastive losses at different layers of an encoder to learn multiple representations from the encoder. Afterward, an ensemble can be constructed to take advantage of the multiple representations for the downstream tasks. We evaluated the proposed method on few-shot learning problems and conducted experiments using the mini-ImageNet and the tiered-ImageNet datasets. Our model achieved the new state-of-the-art results for both datasets, comparing to previous regular, ensemble, and contrastive learing (single-level) based approaches.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 30 of its 33 references that are in the map. First posted on arXiv 15 Jul 2021.
Builds on
30 of 33 references.
References · 30
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2020Improved Baselines with Momentum Contrastive Learningcited by 2,282
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,393
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
- 2018On First-Order Meta-Learning Algorithmscited by 1,003
- 2020What Makes for Good Views for Contrastive Learning?cited by 843
- 2018Meta-Learning with Latent Embedding Optimizationcited by 476
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
18 more
- 2018TADAM: Task dependent adaptive metric for improved few-shot learningcited by 408
- 2018Meta-Transfer Learning for Few-Shot Learningcited by 306
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
- 2019Cross Attention Network for Few-shot Classificationcited by 218
- 2018Recasting Gradient-Based Meta-Learning as Hierarchical Bayescited by 180
- 2020Automatically Discovering and Learning New Visual Categories with Ranking Statisticscited by 141
- 2019Finding Task-Relevant Features for Few-Shot Learning by Category Traversalcited by 101
- 2019Learning to Self-Train for Semi-Supervised Few-Shot Classificationcited by 83
- 2020Embedding Propagation: Smoother Manifold for Few-Shot Classificationcited by 79
- 2020DPGN: Distribution Propagation Graph Network for Few-shot Learningcited by 79
- 2019Diversity with Cooperation: Ensemble Methods for Few-Shot Classificationcited by 70
- 2019An Ensemble of Epoch-wise Empirical Bayes for Few-shot Learningcited by 38
- 2020TAFSSL: Task-Adaptive Feature Sub-Space Learning for few-shot classificationcited by 30
- 2020Semi-Supervised Contrastive Learning with Generalized Contrastive Loss and Its Application to Speaker Recognitioncited by 18
- 2020Spatial Contrastive Learning for Few-Shot Classificationcited by 17
- 2020Meta-Learned Confidence for Few-shot Learningcited by 9
- 2020Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classificationcited by 7
- 2020Few-Shot Image Classification via Contrastive Self-Supervised Learningcited by 5
Built on by
Citing papers per year: 2023: 1.
1 paper.