OOD-CV challenge is an out-of-distribution generalization task. To solve this problem in object detection track, we propose a simple yet effective Generalize-then-Adapt (G&A) framework, which is composed of a two-stage domain generalization part and a one-stage domain adaptation part. The domain generalization part is implemented by a Supervised Model Pretraining stage using source data for model warm-up and a Weakly Semi-Supervised Model Pretraining stage using both source data with box-level label and auxiliary data (ImageNet-1K) with image-level label for performance boosting. The domain adaptation part is implemented as a Source-Free Domain Adaptation paradigm, which only uses the pre-trained model and the unlabeled target data to further optimize in a self-supervised training manner. The proposed G&A framework help us achieve the first place on the object detection leaderboard of the OOD-CV challenge. Code will be released in https://github.com/hikvision-research/OOD-CV.
@article{arxiv.2301.04796,
title = {1st Place Solution for ECCV 2022 OOD-CV Challenge Object Detection Track},
author = {Wei Zhao and Binbin Chen and Weijie Chen and Shicai Yang and Di Xie and Shiliang Pu and Yueting Zhuang},
journal= {arXiv preprint arXiv:2301.04796},
year = {2023}
}