Multi-Target Domain Adaptation with Collaborative Consistency Learning

Abstract

Recently unsupervised domain adaptation for the semantic segmentation task has become more and more popular due to high-cost of pixel-level annotation on real-world images. However, most domain adaptation methods are only restricted to single-source-single-target pair, and can not be directly extended to multiple target domains. In this work, we propose a collaborative learning framework to achieve unsupervised multi-target domain adaptation. An unsupervised domain adaptation expert model is first trained for each source-target pair and is further encouraged to collaborate with each other through a bridge built between different target domains. These expert models are further improved by adding the regularization of making the consistent pixel-wise prediction for each sample with the same structured context. To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights. Extensive experiments demonstrate that the proposed method can effectively exploit rich structured information contained in both labeled source domain and multiple unlabeled target domains. Not only does it perform well across multiple target domains but also performs favorably against state-of-the-art unsupervised domain adaptation methods specially trained on a single source-target pair

arXiv commentCVPR 2021

References in corpus (16)

• Distilling the Knowledge in a Neural Network
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Multi-source Domain Adaptation for Semantic Segmentation
• Revisiting Temporal Modeling for Video Super-resolution
• FDA: Fourier Domain Adaptation for Semantic Segmentation
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories
• Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation
• Differential Treatment for Stuff and Things: A Simple Unsupervised Domain Adaptation Method for Semantic Segmentation
• All about Structure: Adapting Structural Information across Domains for Boosting Semantic Segmentation
• Video Super-Resolution with Recurrent Structure-Detail Network
• Video Super-resolution with Temporal Group Attention

Cited by in corpus (3)

• Semantic Segmentation in Multiple Adverse Weather Conditions with Domain Knowledge Retention
• Multi-Source Domain Adaptation with Collaborative Learning for Semantic Segmentation
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation