Need help with eql.detectron2?
Click the “chat” button below for chat support from the developer who created it, or find similar developers for support.

About the developer

tztztztztz
144 Stars 11 Forks Apache License 2.0 307 Commits 3 Opened issues

Description

The official implementation of Equalization Loss for Long-Tailed Object Recognition (CVPR 2020) based on Detectron2. https://arxiv.org/abs/2003.05176

Services available

!
?

Need anything else?

Contributors list

Equalization Loss for Long-Tailed Object Recognition

Jingru Tan, Changbao Wang, Buyu Li, Quanquan Li, Wanli Ouyang, Changqing Yin, Junjie Yan

[

arXiv
] [
BibTeX
]


In this repository, we release code for Equalization Loss (EQL) in Detectron2. EQL protects the learning for rare categories from being at a disadvantage during the network parameter updating under the long-tailed situation.

Installation

Install Detectron 2 following INSTALL.md. You are ready to go!

LVIS Dataset

Following the instruction of README.md to set up the lvis dataset.

Training

To train a model with 8 GPUs run:

bash
cd /path/to/detectron2/projects/EQL
python train_net.py --config-file configs/eql_mask_rcnn_R_50_FPN_1x.yaml --num-gpus 8

Evaluation

Model evaluation can be done similarly:

bash
cd /path/to/detectron2/projects/EQL
python train_net.py --config-file configs/eql_mask_rcnn_R_50_FPN_1x.yaml --eval-only MODEL.WEIGHTS /path/to/model_checkpoint

Pretrained Models

Instance Segmentation on LVIS

Backbone Method AP AP.r AP.c AP.f AP.bbox download
R50-FPN MaskRCNN 21.2 3.2 21.1 28.7 20.8 model | metrics
R50-FPN MaskRCNN-EQL 24.0 9.4 25.2 28.4 23.6 model | metrics
R50-FPN MaskRCNN-EQL-Resampling 26.1 17.2 27.3 28.2 25.4 model | metrics
R101-FPN MaskRCNN 22.8 4.3 22.7 30.2 22.3 model | metrics
R101-FPN MaskRCNN-EQL 25.9 10.0 27.9 29.8 25.9 model | metrics
R101-FPN MaskRCNN-EQL-Resampling 27.4 17.3 29.0 29.4 27.1 model | metrics

The AP in this repository is higher than that of the origin paper. Because all those models use:

  • Scale jitter
  • Class-specific mask head
  • Better ImageNet pretrain models (of caffe rather than pytorch)

Note that the final results of these configs have large variance across different runs.

Citing EQL

If you use EQL, please use the following BibTeX entry.

@InProceedings{tan2020eql,
  title={Equalization Loss for Long-Tailed Object Recognition},
  author={Jingru Tan, Changbao Wang, Buyu Li, Quanquan Li, 
  Wanli Ouyang, Changqing Yin, Junjie Yan},
  journal={ArXiv:2003.05176},
  year={2020}
}

We use cookies. If you continue to browse the site, you agree to the use of cookies. For more information on our use of cookies please see our Privacy Policy.