Unsupervised domain adaptation for mobile semantic segmentation based on cycle consistency and feature alignment
作者：
Highlights：
• The paper introduces a novel Unsupervised Domain Adaptation (UDA) scheme for semantic segmentation.
• Image translation through adversarial learning is exploited to project labeled source images to the target space.
• We use feature-level discriminators to perform statistical alignment on the latent space defined by the segmentation network.
• Semantic and cycle-consistency constraints are used to preserve semantic and structural properties of images across domains.
• We use a lightweight mobile segmentation network and train the whole framework end-to-end achieving state-of-the-art results.
摘要
•The paper introduces a novel Unsupervised Domain Adaptation (UDA) scheme for semantic segmentation.•Image translation through adversarial learning is exploited to project labeled source images to the target space.•We use feature-level discriminators to perform statistical alignment on the latent space defined by the segmentation network.•Semantic and cycle-consistency constraints are used to preserve semantic and structural properties of images across domains.•We use a lightweight mobile segmentation network and train the whole framework end-to-end achieving state-of-the-art results.
论文关键词：Unsupervised domain adaptation,Semantic segmentation,Adversarial learning,Transfer learning,Image-to-image translation
论文评审过程：Received 12 January 2020, Accepted 26 January 2020, Available online 1 February 2020, Version of Record 22 February 2020.
论文官网地址：https://doi.org/10.1016/j.imavis.2020.103889
