- Notifications
You must be signed in to change notification settings - Fork7
Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics. In CVPR, 2020.
License
NotificationsYou must be signed in to change notification settings
sjenni/LCI
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics[Project Page]
Simon Jenni,Hailin Jin, andPaolo Favaro.
InCVPR, 2020.
This repository contains code for self-supervised pre-training and supervised transfer learning on the STL-10 dataset.
Training and evaluation on ImageNet is coming soon!
The code is based on Python 3.7 and tensorflow 1.15.
- Set the paths to the data and log directories inconstants.py.
- Runinit_datasets.py to download and convert the STL-10 dataset to the TFRecord format:
python init_datasets.py- To train and evaluate a transformation classifier on STL-10 executerun_stl10.py. An example usage could look like this:
python run_stl10.py --tag='test' --num_gpus=1If you find this repository useful for your research, please use the following.
@inproceedings{jenni2020steering, title={Steering Self-Supervised Feature Learning Beyond Local Pixel Statistics}, author={Jenni, Simon and Jin, Hailin and Favaro, Paolo}, booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition}, pages={6408--6417}, year={2020}}