Litcius/Paper detail

Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization

Qianyu Zhou, Chuyun Zhuang, Ran Yi, Xuequan Lu, Lizhuang Ma

20222022 IEEE International Conference on Multimedia and Expo (ICME)32 citationsDOIOpen Access PDF

Abstract

Unsupervised domain adaptation (UDA) for semantic seg-mentation has been well-studied in recent years. However, most existing works largely neglect the local regional consis-tency across different domains, and are less robust to changes in outdoor environments. In this paper, we propose a novel and fully end-to-end trainable approach, called regional contrastive consistency regularization (RCCR) for domain adaptive semantic segmentation. Our core idea is to pull the sim-ilar regional features extracted from the same location of dif-ferent images, i.e., the original image and augmented image, to be closer, and meanwhile push the features from the dif-ferent locations of the two images to be separated. We pro-pose a region-wise contrastive loss with two sampling strate-gies to realize effective regional consistency. Besides, we present momentum projection heads, where the teacher pro-jection head is the exponential moving average of the student. Finally, a memory bank mechanism is designed to learn more robust and stable region-wise features under varying environ-ments. Extensive experiments demonstrate that our approach outperforms the state-of-the-art methods.

Topics & Concepts

Computer scienceSegmentationArtificial intelligenceRegularization (linguistics)Consistency (knowledge bases)Domain (mathematical analysis)Pattern recognition (psychology)MathematicsMathematical analysisDomain Adaptation and Few-Shot LearningMultimodal Machine Learning ApplicationsAdvanced Neural Network Applications
Domain Adaptive Semantic Segmentation via Regional Contrastive Consistency Regularization | Litcius