Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation

Abstract

Unsupervised domain adaptation (UDA) aims to enhance the generalization capability of a certain model from a source domain to a target domain. UDA is of particular significance since no extra effort is devoted to annotating target domain samples. However, the different data distributions in the two domains, or \emph{domain shift/discrepancy}, inevitably compromise the UDA performance. Although there has been a progress in matching the marginal distributions between two domains, the classifier favors the source domain features and makes incorrect predictions on the target domain due to category-agnostic feature alignment. In this paper, we propose a novel category anchor-guided (CAG) UDA model for semantic segmentation, which explicitly enforces category-aware feature alignment to learn shared discriminative features and classifiers simultaneously. First, the category-wise centroids of the source domain features are used as guided anchors to identify the active features in the target domain and also assign them pseudo-labels. Then, we leverage an anchor-based pixel-level distance loss and a discriminative loss to drive the intra-category features closer and the inter-category features further apart, respectively. Finally, we devise a stagewise training mechanism to reduce the error accumulation and adapt the proposed model progressively. Experiments on both the GTA5$\to$Cityscapes and SYNTHIA$\to$Cityscapes scenarios demonstrate the superiority of our CAG-UDA model over the state-of-the-art methods. The code is available at \url{https://github.com/RogerZhangzz/CAG_UDA}.

11 pages, 2 figures, accepted by NeurIPS 2019

Cited by in corpus (15)

• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
• Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things
• Prototypical Pseudo Label Denoising and Target Structure Learning for Domain Adaptive Semantic Segmentation
• Improving Semantic Segmentation via Self-Training
• Instance Adaptive Self-Training for Unsupervised Domain Adaptation
• MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation
• Synergizing between Self-Training and Adversarial Learning for Domain Adaptive Object Detection
• Unsupervised domain adaptation via coarse-to-fine feature alignment method using contrastive learning
• Re-distributing Biased Pseudo Labels for Semi-supervised Semantic Segmentation: A Baseline Investigation
• AutoAdapt: Automated Segmentation Network Search for Unsupervised Domain Adaptation
• Coarse-to-Fine Domain Adaptive Semantic Segmentation with Photometric Alignment and Category-Center Regularization
• Multi-Anchor Active Domain Adaptation for Semantic Segmentation
• Mutual-GAN: Towards Unsupervised Cross-Weather Adaptation with Mutual Information Constraint
• Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation
• MetaPix: Domain Transfer for Semantic Segmentation by Meta Pixel Weighting