A Domain Agnostic Normalization Layer for Unsupervised Adversarial Domain Adaptation

Abstract

We propose a normalization layer for unsupervised domain adaption in semantic scene segmentation. Normalization layers are known to improve convergence and generalization and are part of many state-of-the-art fully-convolutional neural networks. We show that conventional normalization layers worsen the performance of current Unsupervised Adversarial Domain Adaption (UADA), which is a method to improve network performance on unlabeled datasets and the focus of our research. Therefore, we propose a novel Domain Agnostic Normalization layer and thereby unlock the benefits of normalization layers for unsupervised adversarial domain adaptation. In our evaluation, we adapt from the synthetic GTA5 data set to the real Cityscapes data set, a common benchmark experiment, and surpass the state-of-the-art. As our normalization layer is domain agnostic at test time, we furthermore demonstrate that UADA using Domain Agnostic Normalization improves performance on unseen domains, specifically on Apolloscape and Mapillary.

References in corpus (8)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Learning Deconvolution Network for Semantic Segmentation
• Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
• Simultaneous Detection and Segmentation
• Playing for Data: Ground Truth from Computer Games
• On the Effects of Batch and Weight Normalization in Generative Adversarial Networks
• Learning for Disparity Estimation through Feature Constancy
• Rank of Experts: Detection Network Ensemble