Constructing Self-motivated Pyramid Curriculums for Cross-Domain Semantic Segmentation: A Non-Adversarial Approach

Abstract

We propose a new approach, called self-motivated pyramid curriculum domain adaptation (PyCDA), to facilitate the adaptation of semantic segmentation neural networks from synthetic source domains to real target domains. Our approach draws on an insight connecting two existing works: curriculum domain adaptation and self-training. Inspired by the former, PyCDA constructs a pyramid curriculum which contains various properties about the target domain. Those properties are mainly about the desired label distributions over the target domain images, image regions, and pixels. By enforcing the segmentation neural network to observe those properties, we can improve the network's generalization capability to the target domain. Motivated by the self-training, we infer this pyramid of properties by resorting to the semantic segmentation network itself. Unlike prior work, we do not need to maintain any additional models (e.g., logistic regression or discriminator networks) or to solve minmax problems which are often difficult to optimize. We report state-of-the-art results for the adaptation from both GTAV and SYNTHIA to Cityscapes, two popular settings in unsupervised domain adaptation for semantic segmentation.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Rethinking Atrous Convolution for Semantic Image Segmentation
• Learning Transferable Features with Deep Adaptation Networks
• ADVENT: Adversarial Entropy Minimization for Domain Adaptation in Semantic Segmentation
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• A DIRT-T Approach to Unsupervised Domain Adaptation
• Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

Cited by in corpus (14)

• LoveDA: A Remote Sensing Land-Cover Dataset for Domain Adaptive Semantic Segmentation
• Uncertainty-Aware Consistency Regularization for Cross-Domain Semantic Segmentation
• Pixel-Level Cycle Association: A New Perspective for Domain Adaptive Semantic Segmentation
• Unsupervised Domain Adaptation for Mobile Semantic Segmentation based on Cycle Consistency and Feature Alignment
• Improving Semantic Segmentation via Self-Training
• Unsupervised Domain Adaptation in Semantic Segmentation: a Review
• Semantic Distribution-aware Contrastive Adaptation for Semantic Segmentation
• Instance Adaptive Self-Training for Unsupervised Domain Adaptation
• Contextual-Relation Consistent Domain Adaptation for Semantic Segmentation
• Unsupervised Domain Adaptation for Semantic Segmentation via Low-level Edge Information Transfer
• Context-Aware Domain Adaptation in Semantic Segmentation
• CSCL: Critical Semantic-Consistent Learning for Unsupervised Domain Adaptation
• Discovering Latent Classes for Semi-Supervised Semantic Segmentation
• Domain Adaptive Semantic Segmentation without Source Data