Home

Awesome

(ECCV2022) AcroFOD: An Adaptive Method for Cross-domain Few-shot Object Detection

Data Preparation

The links of the processed data (Yolo format) are as follows (in Baidu Desk):

Sim10K Key: juf6 (The synthetic dataset includes only car class.)

KITTI Key: 8brv (The KITTI dataset includes only car class.)

Cityscapes_car_8_1 Key: p69u (The randomly selected 8 images from cityscapes_car.)

Cityscapes_car Key: 4ym4 (The cityscapes dataset includes only car class.)

Cityscapes_8cls Key: rg4z (The Cityscapes dataset includes 8 classes.)

Cityscapes_8cls_foggy Key: bjgr (The Foggy Cityscapes dataset includes 8 classes.)

Viped Key: a9y7 (The synthetic dataset includes)

coco_person_60 Key: vg1m (The randomly selected 60 images from coco_person.)

coco_person Key: je89 (The COCO dataset includes only person class.)

You can also process the raw data to Yolo format via the tools shown here.

Requirements

This repo is based on YOLOv5 repo. Please follow that repo for installation and preparation. The version I built for this project is YOLO v5 3.0. The proposed methods are also easy to be migrated into advanced YOLO versions.

Training

  1. Modify the config of the data in the data subfolders. Please refer to the instructions in the yaml file.

  2. The command below can reproduce the corresponding results mentioned in the paper.

python train_MMD.py --img 640 --batch 12 --epochs 300 --data ./data/city_and_foggy8_1.yaml --cfg ./models/yolov5x.yaml --hyp ./data/hyp_aug/m1.yaml --weights '' --name "test"
@inproceedings{gao2022acrofod,
  title={AcroFOD: An Adaptive Method for Cross-Domain Few-Shot Object Detection},
  author={Gao, Yipeng and Yang, Lingxiao and Huang, Yunmu and Xie, Song and Li, Shiyong and Zheng, Wei-Shi},
  booktitle={European Conference on Computer Vision},
  pages={673--690},
  year={2022}
}