This project hosts the code for implementing the DenseCL algorithm for self-supervised representation learning.

Dense Contrastive Learning for Self-Supervised Visual Pre-Training,
Xinlong Wang, Rufeng Zhang, Chunhua Shen, Tao Kong, Lei Li
In: Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR), 2021
arXiv preprint (arXiv 2011.09157)

• Boosting dense predictions: DenseCL pre-trained models largely benefit dense prediction tasks including object detection and semantic segmentation (up to +2% AP and +3% mIoU).
• Simple implementation: The core part of DenseCL can be implemented in 10 lines of code, thus being easy to use and modify.
• Flexible usage: DenseCL is decoupled from the data pre-processing, thus enabling fast and flexible training while being agnostic about what kind of augmentation is used and how the images are sampled.
• Efficient training: Our method introduces negligible computation overhead (only <1% slower) compared to the baseline method.

• Code and pre-trained models of DenseCL are released. (02/03/2021)

Please refer to INSTALL.md for installation and dataset preparation.

For your convenience, we provide the following pre-trained models on COCO or ImageNet.

Note:

• The metrics for VOC det and seg are AP (COCO-style) and mIoU. The results are averaged over 5 trials.
• The training time is measured on 8 V100 GPUs.
• See our paper for more results on different benchmarks.

./tools/dist_train.sh configs/selfsup/densecl/densecl_coco_800ep.py 8

WORK_DIR=work_dirs/selfsup/densecl/densecl_coco_800ep/
CHECKPOINT=${WORK_DIR}/epoch_800.pth
WEIGHT_FILE=${WORK_DIR}/extracted_densecl_coco_800ep.pth

python tools/extract_backbone_weights.py ${CHECKPOINT} ${WEIGHT_FILE}

Please refer to README.md for transferring to object detection and semantic segmentation.

• After extracting the backbone weights, the model can be used to replace the original ImageNet pre-trained model as initialization for many dense prediction tasks.
• If your machine has a slow data loading issue, especially for ImageNet, your are suggested to convert ImageNet to lmdb format through folder2lmdb_imagenet.py or folder2lmdb_coco.py, and use this config_imagenet or config_coco for training.

We would like to thank the OpenSelfSup for its open-source project and PyContrast for its detection evaluation configs.

Please consider citing our paper in your publications if the project helps your research. BibTeX reference is as follow.

@inproceedings{wang2020DenseCL,
  title={Dense Contrastive Learning for Self-Supervised Visual Pre-Training},
  author={Wang, Xinlong and Zhang, Rufeng and Shen, Chunhua and Kong, Tao and Li, Lei},
  booktitle =  {Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR)},
  year={2021}
}