Kaidi Cao*, Maria Brbić*, Jure Leskovec
This repository contains the PyTorch reference source code of the ORCA algorithm, and its code is explained in detail. ORCA is a pipeline that recognizes previously seen classes and discovers novel, never-before-seen classes at the same time.. For more details please check our paper Open-World Semi-Supervised Learning (ICLR '22).
The code is built with following libraries:
We use SimCLR for pretraining. The weights used in our paper can be downloaded in this link.
- To train on CIFAR-100, run
python orca_cifar.py --dataset cifar100 --labeled-num 50 --labeled-ratio 0.5- To train on ImageNet-100, first use
gen_imagenet_list.pyto generate corresponding splitting lists, then run
python orca_imagenet.py --labeled-num 50 --labeled-ratio 0.5When downloading the dataset fails, try to manually download the dataset and add it to
./dataset
If you find our code useful, please consider citing:
@inproceedings{
cao2022openworld,
title={Open-World Semi-Supervised Learning},
author={Kaidi Cao and Maria Brbic and Jure Leskovec},
booktitle={International Conference on Learning Representations},
year={2022},
url={https://openreview.net/forum?id=O-r8LOR-CCA}
}