Semi-Supervised Domain Adaptation for Semantic Segmentation with Consistency Regularization : A learning framework under scarce dense labels

Abstract: Learning from unlabeled data is a topic of critical significance in machine learning, as the large datasets required to train ever-growing models are costly and impractical to annotate. Semi-Supervised Learning (SSL) methods aim to learn from a few labels and a large unlabeled dataset. In another approach, Domain Adaptation (DA) leverages data from a similar source domain to train a model for a target domain. This thesis focuses on Semi-Supervised Domain Adaptation (SSDA) for the dense task of semantic segmentation, where labels are particularly costly to obtain. SSDA has not received much attention yet, even though it has a great potential and represents a realistic scenario. The few existing SSDA methods for semantic segmentation reuse ideas from Unsupervised DA, despite the di↵erences between the two settings. This thesis proposes a new semantic segmentation framework designed particularly for the SSDA setting. The approach followed was to forego domain alignment and focus instead on enhancing clusterability of target domain features, an idea from SSL. The method is based on consistency regularization, combined with pixel contrastive learning and self-training. The proposed framework is found to be e↵ective not only in SSDA, but also in SSL. Ultimately, a unified solution for SSL and SSDA semantic segmentation is presented. Experiments were conducted on the target dataset of Cityscapes and source dataset of GTA5. The method proposed is competitive in both SSL and SSDA, and sets a new state-of-the-art for SSDA achieving a 65.6% mIoU (+4.4) on Cityscapes with 100 labeled samples. This thesis has an immediate impact on practical applications by proposing a new best-performing framework for the under-explored setting of SSDA. Furthermore, it also contributes towards the more ambitious goal of designing a unified solution for learning from unlabeled data.