GeoNet is a recently proposed domain adaptation benchmark consisting of three challenges (i.e., GeoUniDA, GeoImNet, and GeoPlaces). Each challenge contains images collected from the USA and Asia where there are huge geographical gaps. Our solution adopts a two-stage source-free domain adaptation framework with a Swin Transformer backbone to achieve knowledge transfer from the USA (source) domain to Asia (target) domain. In the first stage, we train a source model using labeled source data with a re-sampling strategy and two types of cross-entropy loss. In the second stage, we generate pseudo labels for unlabeled target data to fine-tune the model. Our method achieves an H-score of 74.56% and ultimately ranks 1st in the GeoUniDA challenge. In GeoImNet and GeoPlaces challenges, our solution also reaches a top-3 accuracy of 64.46% and 51.23%, respectively.

翻译：GeoNet是近期提出的一个域适应基准测试，包含三个挑战（即GeoUniDA、GeoImNet和GeoPlaces）。每个挑战包含来自美国和亚洲的图像数据集，两地存在巨大的地理差异。本方案采用两阶段无源域适应框架，以Swin Transformer为主干网络，实现知识从美国（源域）向亚洲（目标域）的迁移。第一阶段，我们使用带重采样策略和两种交叉熵损失的标记源数据训练源模型。第二阶段，我们为未标记的目标数据生成伪标签以微调模型。本方法在GeoUniDA挑战中取得74.56%的H分数，最终排名第一。在GeoImNet和GeoPlaces挑战中，本方案也分别达到64.46%和51.23%的top-3准确率。