Home

Awesome

<div align="center"><img src="assets/header.png" width="840"></div>

Introduction

This repo contains the official PyTorch implementation of our ICCV paper DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection.

<div align="center"><img src="assets/arch.png" width="800"></div>

Updates!!

Quick Start

1. Check Requirements

2. Build DeFRCN

3. Prepare Data and Weights

4. Training and Evaluation

For ease of training and evaluation over multiple runs, we integrate the whole pipeline of few-shot object detection into one script run_*.sh, including base pre-training and novel-finetuning (both FSOD and G-FSOD).

Results on COCO Benchmark

Results on VOC Benchmark

Acknowledgement

This repo is developed based on TFA and Detectron2. Please check them for more details and features.

Citing

If you use this work in your research or wish to refer to the baseline results published here, please use the following BibTeX entries:

@inproceedings{qiao2021defrcn,
  title={DeFRCN: Decoupled Faster R-CNN for Few-Shot Object Detection},
  author={Qiao, Limeng and Zhao, Yuxuan and Li, Zhiyuan and Qiu, Xi and Wu, Jianan and Zhang, Chi},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision},
  pages={8681--8690},
  year={2021}
}