Adaptive Semantic Segmentation with a Strategic Curriculum of Proxy Labels

Abstract

Training deep networks for semantic segmentation requires annotation of large amounts of data, which can be time-consuming and expensive. Unfortunately, these trained networks still generalize poorly when tested in domains not consistent with the training data. In this paper, we show that by carefully presenting a mixture of labeled source domain and proxy-labeled target domain data to a network, we can achieve state-of-the-art unsupervised domain adaptation results. With our design, the network progressively learns features specific to the target domain using annotation from only the source domain. We generate proxy labels for the target domain using the network's own predictions. Our architecture then allows selective mining of easy samples from this set of proxy labels, and hard samples from the annotated source domain. We conduct a series of experiments with the GTA5, Cityscapes and BDD100k datasets on synthetic-to-real domain adaptation and geographic domain adaptation, showing the advantages of our method over baselines and existing approaches.

References in corpus (12)

• Intriguing properties of neural networks
• Deep Residual Learning for Image Recognition
• Learning Transferable Features with Deep Adaptation Networks
• Unsupervised Domain Adaptation by Backpropagation
• Multi-Scale Context Aggregation by Dilated Convolutions
• The Cityscapes Dataset for Semantic Urban Scene Understanding
• Simple and Scalable Predictive Uncertainty Estimation using Deep Ensembles
• FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
• Adversarial Discriminative Domain Adaptation
• Deep CORAL: Correlation Alignment for Deep Domain Adaptation
• Pyramid Scene Parsing Network
• Playing for Data: Ground Truth from Computer Games

Cited by in corpus (6)

• Self-Training and Adversarial Background Regularization for Unsupervised Domain Adaptive One-Stage Object Detection
• Large-Scale Visual Active Learning with Deep Probabilistic Ensembles
• Regularizing Proxies with Multi-Adversarial Training for Unsupervised Domain-Adaptive Semantic Segmentation
• Dense Uncertainty Estimation
• ST3D: Self-training for Unsupervised Domain Adaptation on 3D Object Detection
• A General Divergence Modeling Strategy for Salient Object Detection