Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation

Abstract

Data-driven based approaches, in spite of great success in many tasks, have poor generalization when applied to unseen image domains, and require expensive cost of annotation especially for dense pixel prediction tasks such as semantic segmentation. Recently, both unsupervised domain adaptation (UDA) from large amounts of synthetic data and semi-supervised learning (SSL) with small set of labeled data have been studied to alleviate this issue. However, there is still a large gap on performance compared to their supervised counterparts. We focus on a more practical setting of semi-supervised domain adaptation (SSDA) where both a small set of labeled target data and large amounts of labeled source data are available. To address the task of SSDA, a novel framework based on dual-level domain mixing is proposed. The proposed framework consists of three stages. First, two kinds of data mixing methods are proposed to reduce domain gap in both region-level and sample-level respectively. We can obtain two complementary domain-mixed teachers based on dual-level mixed data from holistic and partial views respectively. Then, a student model is learned by distilling knowledge from these two teachers. Finally, pseudo labels of unlabeled data are generated in a self-training manner for another few rounds of teachers training. Extensive experimental results have demonstrated the effectiveness of our proposed framework on synthetic-to-real semantic segmentation benchmarks.

CVPR2021

References in corpus (19)

• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• mixup: Beyond Empirical Risk Minimization
• Deep Residual Learning for Image Recognition
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Adversarial Learning for Semi-Supervised Semantic Segmentation
• Pyramid Scene Parsing Network
• Semantic Image Segmentation via Deep Parsing Network
• Playing for Data: Ground Truth from Computer Games
• Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
• Semi-supervised Domain Adaptation via Minimax Entropy
• Adversarial Dropout Regularization
• Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
• Attract, Perturb, and Explore: Learning a Feature Alignment Network for Semi-supervised Domain Adaptation
• Penalizing Top Performers: Conservative Loss for Semantic Segmentation Adaptation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
• MixMatch Domain Adaptaion: Prize-winning solution for both tracks of VisDA 2019 challenge

Cited by in corpus (2)

• Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
• Semi-supervised Domain Adaptation for Semantic Segmentation