A Study on Representation Transfer for Few-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Few-shot classification aims to learn to classify new object categories well using only a few labeled examples. Transferring feature representations from other models is a popular approach for solving few-shot classification problems. In this work we perform a systematic study of various feature representations for few-shot classification, including representations learned from MAML, supervised classification, and several common self-supervised tasks. We find that learning from more complex tasks tend to give better representations for few-shot classification, and thus we propose the use of representations learned from multiple tasks for few-shot classification. Coupled with new tricks on feature selection and voting to handle the issue of small sample size, our direct transfer learning method offers performance comparable to state-of-art on several benchmark datasets.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 35 of its 42 references that are in the map. First posted on arXiv 5 Sep 2022.
Builds on
35 of 42 references.
References · 35
- 2015Deep Residual Learning for Image Recognitioncited by 51,809
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
- 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 11,979
- 2019Momentum Contrast for Unsupervised Visual Representation Learningcited by 7,482
- 2017Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networkscited by 4,861
- 2017Prototypical Networks for Few-shot Learningcited by 3,001
- 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
- 2016Matching Networks for One Shot Learningcited by 2,246
- 2018Unsupervised Representation Learning by Predicting Image Rotationscited by 1,586
- 2016Unsupervised Learning of Visual Representations by Solving Jigsaw Puzzlescited by 1,379
- 2020Big Self-Supervised Models are Strong Semi-Supervised Learnerscited by 1,375
- 2017Learning to Compare: Relation Network for Few-Shot Learningcited by 1,139
23 more
- 2015Unsupervised Visual Representation Learning by Context Predictioncited by 1,062
- 2018On First-Order Meta-Learning Algorithmscited by 1,003
- 2019A Closer Look at Few-shot Classificationcited by 679
- 2019Meta-Learning with Differentiable Convex Optimizationcited by 461
- 2018Meta-Learning for Semi-Supervised Few-Shot Classificationcited by 456
- 2020Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?cited by 435
- 2019A Large-scale Study of Representation Learning with the Visual Task Adaptation Benchmarkcited by 419
- 2019Rapid Learning or Feature Reuse? Towards Understanding the Effectiveness of MAMLcited by 359
- 2019A Baseline for Few-Shot Image Classificationcited by 298
- 2018Few-Shot Learning via Embedding Adaptation with Set-to-Set Functionscited by 293
- 2019Cross Attention Network for Few-shot Classificationcited by 218
- 2017Multi-task Self-Supervised Visual Learningcited by 200
- 2018Large Scale Fine-Grained Categorization and Domain-Specific Transfer Learningcited by 174
- 2019Boosting Few-Shot Visual Learning with Self-Supervisioncited by 140
- 2019Unsupervised Domain Adaptation through Self-Supervisioncited by 116
- 2019Generalized Inner Loop Meta-Learningcited by 92
- 2019When Does Self-supervision Improve Few-shot Learning?cited by 78
- 2018TernausNet: U-Net with VGG11 Encoder Pre-Trained on ImageNet for Image Segmentationcited by 76
- 2019Effectiveness of self-supervised pre-training for speech recognitioncited by 72
- 2019Associative Alignment for Few-shot Image Classificationcited by 58
- 2019A Theoretical Analysis of the Number of Shots in Few-Shot Learningcited by 39
- 2019Meta-Transfer Learning through Hard Taskscited by 23
- 2018DetNet: A Backbone network for Object Detectioncited by 22
Built on by
Not cited yet.