Learning Texture Invariant Representation for Domain Adaptation of Semantic Segmentation

Abstract

Since annotating pixel-level labels for semantic segmentation is laborious, leveraging synthetic data is an attractive solution. However, due to the domain gap between synthetic domain and real domain, it is challenging for a model trained with synthetic data to generalize to real data. In this paper, considering the fundamental difference between the two domains as the texture, we propose a method to adapt to the texture of the target domain. First, we diversity the texture of synthetic images using a style transfer algorithm. The various textures of generated images prevent a segmentation model from overfitting to one specific (synthetic) texture. Then, we fine-tune the model with self-training to get direct supervision of the target texture. Our results achieve state-of-the-art performance and we analyze the properties of the model trained on the stylized dataset with extensive experiments.

arXiv comment2020 CVPR

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• CyCADA: Cycle-Consistent Adversarial Domain Adaptation
• Fast Patch-based Style Transfer of Arbitrary Style
• Synscapes: A Photorealistic Synthetic Dataset for Street Scene Parsing
• Domain Adaptation for Semantic Segmentation with Maximum Squares Loss
• Significance-aware Information Bottleneck for Domain Adaptive Semantic Segmentation

Cited by in corpus (7)

• DSP: Dual Soft-Paste for Unsupervised Domain Adaptive Semantic Segmentation
• A Review of Single-Source Deep Unsupervised Visual Domain Adaptation
• Multi-Target Domain Adaptation with Collaborative Consistency Learning
• Category Contrast for Unsupervised Domain Adaptation in Visual Tasks
• Semi-supervised Domain Adaptation based on Dual-level Domain Mixing for Semantic Segmentation
• Spectral Unsupervised Domain Adaptation for Visual Recognition
• Exploiting Inter-pixel Correlations in Unsupervised Domain Adaptation for Semantic Segmentation