IDA: Informed Domain Adaptive Semantic Segmentation
원문 초록
Mixup-based data augmentation has been validated to be a critical stage in the self-training framework for unsupervised domain adaptive semantic segmentation (UDA-SS), which aims to transfer knowledge from a well-annotated (source) domain to an unlabeled (target) domain. Existing self-training methods usually adopt the popular region-based mixup techniques with a random sampling strategy, which unfortunately ignores the dynamic evolution of different semantics across various domains as training proceeds. To improve the UDA-SS performance, we propose an Informed Domain Adaptation (IDA) model, a self-training framework that mixes the data based on class-level segmentation performance, which aims to emphasize small-region semantics during mixup. In our IDA model, the class-level performance is tracked by an expected confidence score (ECS). We then use a dynamic schedule to determine the mixing ratio for data in different domains. Extensive experimental results reveal that our proposed method is able to outperform the state-of-the-art UDA-SS method by a margin of 1.1 mIoU in the adaptation of GTA-V to Cityscapes and of 0.9 mIoU in the adaptation of SYNTHIA to Cityscapes.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
MASNet: A Robust Deep Marine Animal Segmentation Network
A Novel Unsupervised Domain Adaption Method for Depth-Guided Semantic Segmentation Using Coarse-to-Fine Alignment
Cross-Domain Few-Shot Semantic Segmentation
Pixel-level Intra-domain Adaptation for Semantic Segmentation
EPYNET: Efficient Pyramidal Network for Clothing Segmentation
PDAM: A Panoptic-Level Feature Alignment Framework for Unsupervised Domain Adaptive Instance Segmentation in Microscopy Images
토론
이 논문과 연결된 포럼 글이 아직 없습니다.