This is the PyTorch implementation of our paper:
Unbiased Teacher for Semi-Supervised Object Detection
Yen-Cheng Liu, Chih-Yao Ma, Zijian He, Chia-Wen Kuo, Kan Chen, Peizhao Zhang, Bichen Wu, Zsolt Kira, Peter Vajda
International Conference on Learning Representations (ICLR), 2021
[arXiv] [OpenReview] [Project]
- Linux or macOS with Python ≥ 3.6
- PyTorch ≥ 1.5 and torchvision that matches the PyTorch installation.
# create conda env
conda create -n detectron2 python=3.6
# activate the enviorment
conda activate detectron2
# install PyTorch >=1.5 with GPU
conda install pytorch torchvision -c pytorchFollow the INSTALL.md to install Detectron2.
- Download COCO dataset
# download images
wget http://images.cocodataset.org/zips/train2017.zip
wget http://images.cocodataset.org/zips/val2017.zip
# download annotations
wget http://images.cocodataset.org/annotations/annotations_trainval2017.zip- Organize the dataset as following:
unbiased_teacher/
└── datasets/
└── coco/
├── train2017/
├── val2017/
└── annotations/
├── instances_train2017.json
└── instances_val2017.json- Train the Unbiased Teacher under 1% COCO-supervision
python train_net.py \
--num-gpus 8 \
--config configs/coco_supervision/faster_rcnn_R_50_FPN_sup1_run1.yaml \
SOLVER.IMG_PER_BATCH_LABEL 16 SOLVER.IMG_PER_BATCH_UNLABEL 16- Train the Unbiased Teacher under 2% COCO-supervision
python train_net.py \
--num-gpus 8 \
--config configs/coco_supervision/faster_rcnn_R_50_FPN_sup2_run1.yaml \
SOLVER.IMG_PER_BATCH_LABEL 16 SOLVER.IMG_PER_BATCH_UNLABEL 16- Train the Unbiased Teacher under 5% COCO-supervision
python train_net.py \
--num-gpus 8 \
--config configs/coco_supervision/faster_rcnn_R_50_FPN_sup5_run1.yaml \
SOLVER.IMG_PER_BATCH_LABEL 16 SOLVER.IMG_PER_BATCH_UNLABEL 16- Train the Unbiased Teacher under 10% COCO-supervision
python train_net.py \
--num-gpus 8 \
--config configs/coco_supervision/faster_rcnn_R_50_FPN_sup10_run1.yaml \
SOLVER.IMG_PER_BATCH_LABEL 16 SOLVER.IMG_PER_BATCH_UNLABEL 16python train_net.py \
--resume \
--num-gpus 8 \
--config configs/coco_supervision/faster_rcnn_R_50_FPN_sup10_run1.yaml \
SOLVER.IMG_PER_BATCH_LABEL 16 SOLVER.IMG_PER_BATCH_UNLABEL 16 MODEL.WEIGHTS <your weight>.pthpython train_net.py \
--eval-only \
--num-gpus 8 \
--config configs/coco_supervision/faster_rcnn_R_50_FPN_sup10_run1.yaml \
SOLVER.IMG_PER_BATCH_LABEL 16 SOLVER.IMG_PER_BATCH_UNLABEL 16 MODEL.WEIGHTS <your weight>.pthFor the following results, we use 16 labeled images + 16 unlabeled images on 8 GPUs (single node).
Faster-RCNN:
| Model | Supervision | Batch size | AP | Model Weights |
|---|---|---|---|---|
| R50-FPN | 1% | 16 labeled img + 16 unlabeled imgs | 20.16 | link |
| R50-FPN | 2% | 16 labeled img + 16 unlabeled imgs | 24.16 | link |
| R50-FPN | 5% | 16 labeled img + 16 unlabeled imgs | 27.84 | link |
| R50-FPN | 10% | 16 labeled img + 16 unlabeled imgs | 31.39 | link |
- Q: Using the lower batch size and fewer GPUs cannot achieve the results presented in the paper?
- A: We train the model with 32 labeled images + 32 unlabeled images per batch for the results presented in the paper, and using the lower batch size leads to lower accuracy. For example, in the 1% COCO-supervision setting, the model trained with 16 labeled images + 16 unlabeled images achieves 19.9 AP as shown in the following table.
| Experiment GPUs | Batch size per node | Batch size | AP |
|---|---|---|---|
| 8 GPUs/node; 4 nodes | 8 labeled imgs + 8 unlabeled imgs | 32 labeled img + 32 unlabeled imgs | 20.75 |
| 8 GPUs/node; 1 node | 16 labeled imgs + 16 unlabeled imgs | 16 labeled imgs + 16 unlabeled imgs | 20.16 |
If you use Unbiased Teacher in your research or wish to refer to the results published in the paper, please use the following BibTeX entry.
@inproceedings{liu2021unbiased,
title={Unbiased Teacher for Semi-Supervised Object Detection},
author={Liu, Yen-Cheng and Ma, Chih-Yao and He, Zijian and Kuo, Chia-Wen and Chen, Kan and Zhang, Peizhao and Wu, Bichen and Kira, Zsolt and Vajda, Peter},
booktitle={Proceedings of the International Conference on Learning Representations (ICLR)},
year={2021},
}Also, if you use Detectron2 in your research, please use the following BibTeX entry.
@misc{wu2019detectron2,
author = {Yuxin Wu and Alexander Kirillov and Francisco Massa and
Wan-Yen Lo and Ross Girshick},
title = {Detectron2},
howpublished = {\url{https://github.com/facebookresearch/detectron2}},
year = {2019}
}This project is licensed under MIT License, as found in the LICENSE file.