A Fully Convolutional Tri-branch Network (FCTN) for Domain Adaptation
arXiv:1711.03694
Abstract
A domain adaptation method for urban scene segmentation is proposed in this work. We develop a fully convolutional tri-branch network, where two branches assign pseudo labels to images in the unlabeled target domain while the third branch is trained with supervision based on images in the pseudo-labeled target domain. The re-labeling and re-training processes alternate. With this design, the tri-branch network learns target-specific discriminative representations progressively and, as a result, the cross-domain capability of the segmenter improves. We evaluate the proposed network on large-scale domain adaptation experiments using both synthetic (GTA) and real (Cityscapes) images. It is shown that our solution achieves the state-of-the-art performance and it outperforms previous methods by a significant margin.
Accepted by ICASSP 2018
References in corpus (7)
- Learning Transferable Features with Deep Adaptation Networks
- FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
- Curriculum Domain Adaptation for Semantic Segmentation of Urban Scenes
- Asymmetric Tri-training for Unsupervised Domain Adaptation
- Deep CORAL: Correlation Alignment for Deep Domain Adaptation
- Playing for Data: Ground Truth from Computer Games
- Multiple Instance Curriculum Learning for Weakly Supervised Object Detection