Revisiting Self-Supervised Visual Representation Learning
Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised techniques achieves superior performance on many challenging be...
Saved in:
Published in | 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) pp. 1920 - 1929 |
---|---|
Main Authors | , , |
Format | Conference Proceeding |
Language | English |
Published |
IEEE
01.06.2019
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Unsupervised visual representation learning remains a largely unsolved problem in computer vision research. Among a big body of recently proposed approaches for unsupervised learning of visual representations, a class of self-supervised techniques achieves superior performance on many challenging benchmarks. A large number of the pretext tasks for self-supervised learning have been studied, but other important aspects, such as the choice of convolutional neural networks (CNN), has not received equal attention. Therefore, we revisit numerous previously proposed self-supervised models, conduct a thorough large scale study and, as a result, uncover multiple crucial insights. We challenge a number of common practices in self-supervised visual representation learning and observe that standard recipes for CNN design do not always translate to self-supervised representation learning. As part of our study, we drastically boost the performance of previously proposed techniques and outperform previously published state-of-the-art results by a large margin. We will release the code for reproducing our experiments when the anonymity requirements are lifted. |
---|---|
ISSN: | 2575-7075 |
DOI: | 10.1109/CVPR.2019.00202 |