MMDetection/configs/instaboost

• InstaBoost for MMDetection
• • Usage
  • • Requirements
    • Integration with MMDetection
  • Results and Models

InstaBoost for MMDetection

Configs in this directory is the implementation for ICCV2019 paper "InstaBoost: Boosting Instance Segmentation Via Probability Map Guided Copy-Pasting" and provided by the authors of the paper. InstaBoost is a data augmentation method for object detection and instance segmentation. The paper has been released on arXiv.

@inproceedings{fang2019instaboost,
  title={Instaboost: Boosting instance segmentation via probability map guided copy-pasting},
  author={Fang, Hao-Shu and Sun, Jianhua and Wang, Runzhong and Gou, Minghao and Li, Yong-Lu and Lu, Cewu},
  booktitle={Proceedings of the IEEE International Conference on Computer Vision},
  pages={682--691},
  year={2019}
}

Usage

Requirements

You need to install instaboostfast before using it.

pip install instaboostfast

The code and more details can be found here.

Integration with MMDetection

InstaBoost have been already integrated in the data pipeline, thus all you need is to add or change InstaBoost configurations after LoadImageFromFile. We have provided examples like this. You can refer to InstaBoostConfig for more details.

Results and Models

• All models were trained on coco_2017_train and tested on coco_2017_val for conveinience of evaluation and comparison. In the paper, the results are obtained from test-dev.
• To balance accuracy and training time when using InstaBoost, models released in this page are all trained for 48 Epochs. Other training and testing configs strictly follow the original framework.
• For results and models in MMDetection V1.x, please refer to Instaboost.

Network	Backbone	Lr schd	Mem (GB)	Inf time (fps)	box AP	mask AP	Download
Mask R-CNN	R-50-FPN	4x	4.4	17.5	40.6	36.6	model | log
Mask R-CNN	R-101-FPN	4x	6.4		42.5	38.0	model | log
Mask R-CNN	X-101-64x4d-FPN	4x	10.7		44.7	39.7	model | log
Cascade R-CNN	R-101-FPN	4x	6.0	12.0	43.7	38.0	model | log