To refer to this page use:
|Abstract:||Recent advances have spurred incredible progress in self-supervised pretraining for vision. We investigate what factors may play a role in the utility of these pretraining methods for practitioners. To do this, we evaluate various self-supervised algorithms across a comprehensive array of synthetic datasets and downstream tasks. We prepare a suite of synthetic data that enables an endless supply of annotated images as well as full control over dataset difficulty. Our experiments offer insights into how the utility of self-supervision changes as the number of available labels grows as well as how the utility changes as a function of the downstream task and the properties of the training data. We also find that linear evaluation does not correlate with finetuning performance. Code and data is available at github.com/princeton-vl/selfstudy.|
|Citation:||Newell, Alejandro, and Jia Deng. "How Useful is Self-Supervised Pretraining for Visual Tasks?." IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020): pp. 7343-7352. doi:10.1109/CVPR42600.2020.00737|
|Pages:||7343 - 7352|
|Type of Material:||Conference Article|
|Journal/Proceeding Title:||IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)|
Items in OAR@Princeton are protected by copyright, with all rights reserved, unless otherwise indicated.