Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey

Volpi, R.; Chidlovskii, Boris

doi:10.48550/arxiv.2112.03241

Cited by 6 publications

(8 citation statements)

References 190 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The initial focus of DA in CV was on simple CV tasks -like digit recognition and image classification, but later, the focus included complex tasks of object detection, segmentation, depth estimation and similar. Surveys have been done on domain adaptation on specific computer vision tasks, e.g., semantic segmentation [294] and object detection [295]. The current focus is increasingly on even more complex tasks (e.g., pose estimation, video classification), complex datasets (e.g., in the wild, 3D), improve state-of-the-art DA metrics in previously mentioned tasks.…”

Section: A Computer Vision (Cv) Domain Adaptation Usagementioning

confidence: 99%

Domain Adaptation: Challenges, Methods, Datasets, and Applications

et al. 2023

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) trained on one dataset (source domain) do not perform well on another set of data (target domain), which is different but has similar properties as the source domain. Domain Adaptation (DA) strives to alleviate this problem and has great potential in its application in practical settings, real-world scenarios, industrial applications and many data domains. Various DA methods aimed at individual data domains have been reported in the last few years; however, there is no comprehensive survey that encompasses all these data domains, focuses on the datasets available, the methods relevant to each domain, and importantly the applications and challenges. To that end, this survey paper discusses how DA can help DNNs work efficiently in these settings by reviewing DA methods and techniques. We have considered five data domains: computer vision, natural language processing, speech, time-series, and multi-modal data. We present a comprehensive taxonomy, including the methods, datasets, challenges, and applications corresponding to each domain. Our goal is to discuss industrial use cases and DA implementation for those. Our final aim is to provide future research directions based on evolving methods and results, the datasets used, and industrial applications.

show abstract

Section: A Computer Vision (Cv) Domain Adaptation Usagementioning

confidence: 99%

Domain Adaptation: Challenges, Methods, Datasets, and Applications

et al. 2023

View full text Add to dashboard Cite

show abstract

“…UDA in Semantic Segmentation 1) Domain Alignment. : We review the domain alignment methods in UDA semantic segmentation, including pixel-, feature-, and output-level alignment in a public space [33], [34]. Alignment at pixel level: Works along this line attempt to unify the visual appearance differences of the source and target domain.…”

Section: Related Workmentioning

confidence: 99%

Cluster Alignment With Target Knowledge Mining for Unsupervised Domain Adaptation Semantic Segmentation

Wang

Dong

Zhang

et al. 2022

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) carries out knowledge transfer from the labeled source domain to the unlabeled target domain. Existing feature alignment methods in UDA semantic segmentation achieve this goal by aligning the feature distribution between domains. However, these feature alignment methods ignore the domain-specific knowledge of the target domain. In consequence, 1) the correlation among pixels of the target domain is not explored; and 2) the classifier is not explicitly designed for the target domain distribution. To conquer these obstacles, we propose a novel cluster alignment framework, which mines the domain-specific knowledge when performing the alignment. Specifically, we design a multi-prototype clustering strategy to make the pixel features within the same class tightly distributed for the target domain. Subsequently, a contrastive strategy is developed to align the distributions between domains, with the clustered structure maintained. After that, a novel affinity-based normalized cut loss is devised to learn taskspecific decision boundaries. Our method enhances the model's adaptability in the target domain, and can be used as a preadaptation for self-training to boost its performance. Sufficient experiments prove the effectiveness of our method against existing state-of-the-art methods on representative UDA benchmarks.

show abstract

“…Using a synthetic dataset, however, comes at the cost of a domain shift, which is often strongly associated with appearance changes [34]. When the source (synthetic images) and target (real images) domains are semantically related, but are different in visual representation, direct propagation of learned knowledge about one domain to another can adversely affect segmentation performance in the latter domain.…”

Section: Introductionmentioning

confidence: 99%

Synthetic-to-Real Composite Semantic Segmentation in Additive Manufacturing

Petsiuk,

Singh,

Dadhwal

et al. 2024

JMMP

View full text Add to dashboard Cite

The application of computer vision and machine learning methods for semantic segmentation of the structural elements of 3D-printed products in the field of additive manufacturing (AM) can improve real-time failure analysis systems and potentially reduce the number of defects by providing additional tools for in situ corrections. This work demonstrates the possibilities of using physics-based rendering for labeled image dataset generation, as well as image-to-image style transfer capabilities to improve the accuracy of real image segmentation for AM systems. Multi-class semantic segmentation experiments were carried out based on the U-Net model and the cycle generative adversarial network. The test results demonstrated the capacity of this method to detect such structural elements of 3D-printed parts as a top (last printed) layer, infill, shell, and support. A basis for further segmentation system enhancement by utilizing image-to-image style transfer and domain adaptation technologies was also considered. The results indicate that using style transfer as a precursor to domain adaptation can improve real 3D printing image segmentation in situations where a model trained on synthetic data is the only tool available. The mean intersection over union (mIoU) scores for synthetic test datasets included 94.90% for the entire 3D-printed part, 73.33% for the top layer, 78.93% for the infill, 55.31% for the shell, and 69.45% for supports.

show abstract

Unsupervised Domain Adaptation for Semantic Image Segmentation: a Comprehensive Survey

Cited by 6 publications

References 190 publications

Domain Adaptation: Challenges, Methods, Datasets, and Applications

Domain Adaptation: Challenges, Methods, Datasets, and Applications

Cluster Alignment With Target Knowledge Mining for Unsupervised Domain Adaptation Semantic Segmentation

Synthetic-to-Real Composite Semantic Segmentation in Additive Manufacturing

Contact Info

Product

Resources

About