FewX

FewX is an open source toolbox on top of Detectron2 for data-limited instance-level recognition tasks, e.g., few-shot object detection, few-shot instance segmentation, partially supervised instance segmentation and so on.

All data-limited instance-level recognition works from Qi Fan (HKUST, fanqithu@gmail.com) are open-sourced here.

To date, FewX implements the following algorithms:

FSOD: few-shot object detection.
CPMask: partially supervised/fully supervised/few-shot instance segmentation (to be released).

Highlights

State-of-the-art performance.
- FSOD is the best few-shot object detection model.
- CPMask is the best partially supervised/few-shot instance segmentation model.

Updates

FewX has been released. (09/08/2020)

Results on MS COCO

Few Shot Object Detection

Method	Training Dataset	Evaluation way&shot	box AP	download
FSOD (paper)	COCO (non-voc)	full-way 10-shot	11.1	-
FSOD (this implementation)	COCO (non-voc)	full-way 10-shot	12.0	model \| metrics

The results are reported on the COCO voc subset with ResNet-50 backbone.

You can reference the original FSOD implementation on the Few-Shot-Object-Detection-Dataset.

Installation

You only need to install detectron2. We recommend the Pre-Built Detectron2 (Linux only) version with pytorch 1.5.

Prepare dataset

Prepare for coco dataset following this instruction.
cd datasets, change the DATA_ROOT in the generate_support_data.sh to your data path.
sh generate_support_data.sh.

Training and Evaluation

Just run sh all.sh in the root dir. (This script uses 4 GPUs. You can change the GPU number.)

TODO

Add other dataset results to FSOD.
Add CPMask code with partially supervised instance segmentation, fully supervised instance segmentation and few-shot instance segmentation.

Citing FewX

If you use this toolbox in your research or wish to refer to the baseline results, please use the following BibTeX entries.

@inproceedings{fan2020fsod,
  title={Few-Shot Object Detection with Attention-RPN and Multi-Relation Detector},
  author={Fan, Qi and Zhuo, Wei and Tang, Chi-Keung and Tai, Yu-Wing},
  booktitle={CVPR},
  year={2020}
  
}
@inproceedings{fan2020cpmask,
  title={Commonality-Parsing Network across Shape and Appearance for Partially Supervised Instance Segmentation},
  author={Fan, Qi and Ke, Lei and Pei, Wenjie and Tang, Chi-Keung and Tai, Yu-Wing},
  booktitle={ECCV},
  year={2020}
}

Special Thanks

Detectron2, AdelaiDet, centermask2

gaowq2017 / FewX