Iterative Loop Method Combining Active and Semi-Supervised Learning for Domain Adaptive Semantic Segmentation

Abstract

Recently, self-training and active learning have been proposed to alleviate this problem. Self-training can improve model accuracy with massive unlabeled data, but some pseudo labels containing noise would be generated with limited or imbalanced training data. And there will be suboptimal models if human guidance is absent. Active learning can select more effective data to intervene, while the model accuracy can not be improved because the massive unlabeled data are not used. And the probability of querying sub-optimal samples will increase when the domain difference is too large, increasing annotation cost. This paper proposes an iterative loop learning method combining Self-Training and Active Learning (STAL) for domain adaptive semantic segmentation. The method first uses self-training to learn massive unlabeled data to improve model accuracy and provide more accurate selection models for active learning. Secondly, combined with the sample selection strategy of active learning, manual intervention is used to correct the self-training learning. Iterative loop to achieve the best performance with minimal label cost. Extensive experiments show that our method establishes stateof-the-art performance on tasks of GTAV → Cityscapes, SYNTHIA → Cityscapes, improving by 4.9% mIoU and 5.2% mIoU, compared to the previous best method, respectively. Code will be available.

FDDS: Feature Disentangling and Domain Shifting for Domain Adaptation

“…Many methods (such as LC [14] and DRANet [15]) use GTA5 and Cityscapes as source and target domain, respectively, for unsupervised domain adaptation tasks. Compared with some methods, such as [47,48] which completed 13 classes of SYNTHIA [49] to the Cityscapes [46] task, our 19 classes task was more complex and better reflected the performance of domain adaptation.…”