MLAN: Multi-Level Adversarial Network for Domain Adaptive Semantic Segmentation

Abstract

Recent progresses in domain adaptive semantic segmentation demonstrate the effectiveness of adversarial learning (AL) in unsupervised domain adaptation. However, most adversarial learning based methods align source and target distributions at a global image level but neglect the inconsistency around local image regions. This paper presents a novel multi-level adversarial network (MLAN) that aims to address inter-domain inconsistency at both global image level and local region level optimally. MLAN has two novel designs, namely, region-level adversarial learning (RL-AL) and co-regularized adversarial learning (CR-AL). Specifically, RL-AL models prototypical regional context-relations explicitly in the feature space of a labelled source domain and transfers them to an unlabelled target domain via adversarial learning. CR-AL fuses region-level AL and image-level AL optimally via mutual regularization. In addition, we design a multi-level consistency map that can guide domain adaptation in both input space ($i.e.$, image-to-image translation) and output space ($i.e.$, self-training) effectively. Extensive experiments show that MLAN outperforms the state-of-the-art with a large margin consistently across multiple datasets.

Accepted to Pattern Recognition, 2022

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Deep Domain Confusion: Maximizing for Domain Invariance
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Category Anchor-Guided Unsupervised Domain Adaptation for Semantic Segmentation
• FSDR: Frequency Space Domain Randomization for Domain Generalization
• Cross-View Regularization for Domain Adaptive Panoptic Segmentation

Cited by in corpus (4)

• Model Adaptation: Historical Contrastive Learning for Unsupervised Domain Adaptation without Source Data
• Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
• Semi-Supervised Domain Adaptation via Adaptive and Progressive Feature Alignment
• Spectral Unsupervised Domain Adaptation for Visual Recognition