Journal
IEEE TRANSACTIONS ON IMAGE PROCESSING
Volume 28, Issue 9, Pages 4376-4386Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIP.2019.2910667
Keywords
Semantic segmentation; domain adaptation; adversarial learning; weakly supervision
Funding
- National Natural Science Foundation of China [U1864204, 61773316]
- Natural Science Foundation of Shaanxi Province [2018KJXX-024]
- Project of Special Zone for National Defense Science and Technology Innovation
Ask authors/readers for more resources
Semantic segmentation, a pixel-level vision task, is rapidly developed by using convolutional neural networks (CNNs). Training CNNs requires a large amount of labeled data, but manually annotating data is difficult. For emancipating manpower, in recent years, some synthetic datasets are released. However, they are still different from real scenes, which causes that training a model on the synthetic data (source domain) cannot achieve a good performance on real urban scenes (target domain). In this paper, we propose a weakly supervised adversarial domain adaptation to improve the segmentation performance from synthetic data to real scenes, which consists of three deep neural networks. A detection and segmentation (DS) model focuses on detecting objects and predicting segmentation map; a pixel-level domain classifier (PDC) tries to distinguish the image features from which domains; and an object-level domain classifier (ODC) discriminates the objects from which domains and predicts object classes. PDC and ODC are treated as the discriminators, and DS is considered as the generator. By the adversarial learning, DS is supposed to learn domain-invariant features. In experiments, our proposed method yields the new record of mIoU metric in the same problem.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available