Unsupervised Domain Adaptation with Implicit Pseudo Supervision for Semantic Segmentation
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2022 International Joint Conference on Neural Networks (IJCNN), 2022, 2022-July, pp. 1-10
- Issue Date:
- 2022-09-30
Closed Access
| Filename | Description | Size | |||
|---|---|---|---|---|---|
| Unsupervised_Domain_Adaptation_with_Implicit_Pseudo_Supervision_for_Semantic_Segmentation.pdf | Published version | 7.18 MB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Pseudo labelling is a popular technique in unsupervised domain adaptation for semantic segmentation However pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and training process In this paper we train the model by the pseudo labels which are implicitly produced by itself to learn new complementary knowledge about target domain Specifically we propose a tri learning architecture where every two branches produce the pseudo labels to train the third one And we align the pseudo labels based on the similarity of the probability distributions for each two branches To further implicitly utilize the pseudo labels we maximize the distances of features for different classes and minimize the distances for the same classes by triplet loss Extensive experiments on GTA5 to Cityscapes and SYNTHIA to Cityscapes tasks show that the proposed method has considerable improvements
Please use this identifier to cite or link to this item: