A Fully Convolutional Tri-Branch Network (FCTN) for Domain Adaptation
By Junting Zhang, Liang Chen, C.-C. Jay Kuo. 2017
25 citations recorded by the source corpus.
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.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Yi Yang
- Trevor Darrell
- Kate Saenko
- Judy Hoffman
- Mingsheng Long
- Luc Van Gool
- Jianmin Wang
- Dacheng Tao
In Computer Vision and Pattern Recognition
- Yi Yang
- Luc Van Gool
- Trevor Darrell
- Dacheng Tao
- Ming-Hsuan Yang
- Xiaogang Wang
- Jitendra Malik
- Andrea Vedaldi
Citations in the corpus
- Class-incremental Learning via Deep Model Consolidation (2019, background): “tinaNet [31]. Exploiting external data. In computer vision, the idea of employing external data to improve performance of a target task has been explored in many contexts. Inductive transfer learning [11,58] aims to transfer and reuse knowledge in labeled out-of-domain instances. Semi-supervised lea”
- CyCADA: Cycle-Consistent Adversarial Domain Adaptation (2017, background): “Zhang et al. (2017) instead perform segmentation adaptation by aligning label distributions both globally and across superpixels in an image.”
- Taking a Closer Look at Domain Shift: Category-Level Adversaries for Semantics Consistent Domain Adaptation (2018, methodology): “Similar to co-training, tri-training keeps the two classifiers producing pseudo labels and uses these pseudo labels to train an extra classifier [32, 43].”