Unsupervised Domain Adaptation (UDA) aims to transfer knowledge learned from
a labeled source domain to an unlabeled target domain. While UDA methods for
synthetic to real-world domains (synth-to-real) show remarkable performance in
tasks such as semantic segmentation and object detection, very few were
proposed for the instance segmentation task. In this paper, we introduce
UDA4Inst, a model of synth-to-real UDA for instance segmentation in autonomous
driving. We propose a novel cross-domain bidirectional data mixing method at
the instance level to fully leverage the data from both source and target
domains. Rare-class balancing and category module training are also employed to
further improve the performance. It is worth noting that we are the first to
demonstrate results on two new synth-to-real instance segmentation benchmarks,
with 39.0 mAP on UrbanSyn->Cityscapes and 35.7 mAP on Synscapes->Cityscapes.
UDA4Inst also achieves the state-of-the-art result on SYNTHIA->Cityscapes with
31.3 mAP, +15.6 higher than the latest approach. Our code will be released.

UDA4Inst 是一种适用于自动驾驶中实例分割的合成到真实领域无监督域适应模型，通过引入新颖的交叉域双向实例级混合数据方法充分利用了源域和目标域的数据，并采用稀有类别平衡和类别模块训练进一步提高了性能。在新的合成到真实实例分割基准测试上，UDA4Inst 分别在 UrbanSyn->Cityscapes 和 Synscapes->Cityscapes 上达到了 39.0 mAP 和 35.7 mAP，同时在 SYNTHIA->Cityscapes 上的性能为 31.3 mAP，比最新方法高出 15.6。