CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency

Abstract

Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e.g., synthetic to real images). The adapted representations often do not capture pixel-level domain shifts that are crucial for dense prediction tasks (e.g., semantic segmentation). In this paper, we present a novel pixel-wise adversarial domain adaptation algorithm. By leveraging image-to-image translation methods for data augmentation, our key insight is that while the translated images between domains may differ in styles, their predictions for the task should be consistent. We exploit this property and introduce a cross-domain consistency loss that enforces our adapted model to produce consistent predictions. Through extensive experimental results, we show that our method compares favorably against the state-of-the-art on a wide variety of unsupervised domain adaptation tasks.

Code: https://github.com/YunChunChen/CrDoCo-pytorch Project: https://yunchunchen.github.io/CrDoCo/

References in corpus (12)

• Learning Transferable Features with Deep Adaptation Networks
• Depth Map Prediction from a Single Image using a Multi-Scale Deep Network
• Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
• Unsupervised Domain Adaptation with Residual Transfer Networks
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Adversarial Discriminative Domain Adaptation
• Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
• Domain Stylization: A Strong, Simple Baseline for Synthetic to Real Image Domain Adaptation
• DeepMVS: Learning Multi-view Stereopsis
• Recover and Identify: A Generative Dual Model for Cross-Resolution Person Re-Identification