Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?
Name
2003.11539.pdf
Size
1.98 MB
Format
Adobe PDF
Checksum (MD5)
fc5ebd0bb40ef7892b7acf33bfe76a66
Author(s)
Tian, Yonglong
Wang, Yue
Tenenbaum, Joshua B
Isola, Phillip John
Date Issued
August 2020
Journal
ECCV 2020: Computer Vision – ECCV 2020
Publisher
Springer
Citation
Tian, Yonglong et al. “Rethinking Few-Shot Image Classification: a Good Embedding Is All You Need?” In Proceedings of the ECCV 2020: Computer Vision – ECCV 2020, Glasgow, UK, August 23-28, 2020, Springer, (August 2020): 266-282 © 2020 The Author(s)
Version
Original manuscript
Abstract
The focus of recent meta-learning research has been onthe development of learning algorithms that can quicklyadapt to test time tasks with limited data and low compu-tational cost. Few-shot learning is widely used as one ofthe standard benchmarks in meta-learning. In this work, weshow that a simple baseline: learning a supervised or self-supervised representation on the meta-training set, followedby training a linear classifier on top of this representation,outperforms state-of-the-art few-shot learning methods. Anadditional boost can be achieved through the use of self-distillation. This demonstrates that using a good learnedembedding model can be more effective than sophisticatedmeta-learning algorithms. We believe that our findings mo-tivate a rethinking of few-shot image classification bench-marks and the associated role of meta-learning algorithms.Code is available at:http://github.com/WangYueFt/rfs/.
MIT Department
Massachusetts Institute of Technology. Department of Brain and Cognitive Sciences
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
https://doi.org/10.1007/978-3-030-58568-6_16
