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.

翻译：OOD-CV 挑战是一个超出分布范围的一般性任务。 为了解决物体探测轨道上的这个问题, 我们提议了一个简单而有效的通用- 现成- 适应( G&A) 框架( G&A) 框架, 由两阶段域通用部分和一阶段域适应部分组成。 域通用部分由监督示范培训阶段实施, 使用模型热度源数据和弱半半超模示范培训阶段, 使用带有箱级标签的源数据, 以及带有图像级标签的辅助数据( ImageNet-1K ), 增强性能。 域适应部分作为无源域适应范例实施, 仅使用预先培训的模式和无标签的目标数据, 以自我监督的培训方式进一步优化。 拟议的 G&A 框架帮助我们在OD- CV 挑战的物体探测领导板上取得第一位位置。 代码将在 https://github.com/ hikvision- reearch/ OOD- CV 中发布。