Uncertainty Reduction for Model Adaptation in Semantic Segmentation

Traditional methods for Unsupervised Domain Adaptation (UDA) targeting semantic segmentation exploit information common to the source and target domains, using both labeled source data and unlabeled target data. In this paper, we investigate a setting where the source data is unavailable, but the classifier trained on the source data is; hence named "model adaptation". Such a scenario arises when data sharing is prohibited, for instance, because of privacy, or Intellectual Property (IP) issues. To tackle this problem, we propose a method that reduces the uncertainty of predictions on the target domain data. We accomplish this in two ways: minimizing the entropy of the predicted posterior, and maximizing the noise robustness of the feature representation. We show the efficacy of our method on the transfer of segmentation from computer generated images to real-world driving images, and transfer between data collected in different cities, and surprisingly reach performance comparable with that of the methods that have access to source data.