• Corpus ID: 239049377

Semi-supervised Domain Adaptation for Semantic Segmentation

  title={Semi-supervised Domain Adaptation for Semantic Segmentation},
  author={Ying Chen and Xu Ouyang and Kaiyue Zhu and Gady Agam},
Deep learning approaches for semantic segmentation rely primarily on supervised learning approaches and require substantial efforts in producing pixel-level annotations. Further, such approaches may perform poorly when applied to unseen image domains. To cope with these limitations, both unsupervised domain adaptation (UDA) with full source supervision but without target supervision and semisupervised learning (SSL) with partial supervision have been proposed. While such methods are effective… 

Figures and Tables from this paper


Unsupervised Domain Adaptation for Semantic Segmentation via Class-Balanced Self-training
This paper proposes a novel UDA framework based on an iterative self-training (ST) procedure, where the problem is formulated as latent variable loss minimization, and can be solved by alternatively generating pseudo labels on target data and re-training the model with these labels.
Domain Adaptation for Semantic Segmentation With Maximum Squares Loss
The maximum squares loss prevents the training process being dominated by easy-to-transfer samples in the target domain, and introduces the image-wise weighting ratio to alleviate the class imbalance in the unlabeled target domain.
DADA: Depth-Aware Domain Adaptation in Semantic Segmentation
This work proposes a unified depth-aware UDA framework that leverages in several complementary ways the knowledge of dense depth in the source domain, and achieves state-of-the-art performance on different challenging synthetic-2-real benchmarks.
Bidirectional Learning for Domain Adaptation of Semantic Segmentation
A self-supervised learning algorithm to learn a better segmentation adaptation model and in return improve the image translation model and the bidirectional learning framework for domain adaptation of segmentation is proposed.
Mask-based Data Augmentation for Semi-supervised Semantic Segmentation
This paper proposes a new approach for data augmentation, termed ComplexMix, which incorporates aspects of CutMix and ClassMix with improved performance and has the ability to control the complexity of the augmented data while attempting to be semantically-correct and address the tradeoff between complexity and correctness.
Semi-Supervised Semantic Segmentation With High- and Low-Level Consistency
This work proposes an approach for semi-supervised semantic segmentation that learns from limited pixel-wise annotated samples while exploiting additional annotation-free images, and achieves significant improvement over existing methods, especially when trained with very few labeled samples.
Learning to Adapt Structured Output Space for Semantic Segmentation
A multi-level adversarial network is constructed to effectively perform output space domain adaptation at different feature levels and it is shown that the proposed method performs favorably against the state-of-the-art methods in terms of accuracy and visual quality.
Semi-Supervised Semantic Segmentation via Dynamic Self-Training and Class-Balanced Curriculum
The method, Dynamic Self-Training and Class-Balanced Curriculum (DST-CBC), exploits inter-model disagreement by prediction confidence to construct a dynamic loss robust against pseudo label noise, enabling it to extend pseudo labeling to a class-balanced curriculum learning process.
Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
A novel category anchor-guided (CAG) UDA model for semantic segmentation is proposed, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously.
Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
This paper relies on representative prototypes, the feature centroids of classes, to address the two issues for unsupervised domain adaptation and exploits the feature distances from prototypes that provide richer information than mere prototypes to exploit the likelihood of pseudo labels.