BAPA-Net: Boundary Adaptation and Prototype Alignment for Cross-domain Semantic Segmentation

By Yahao Liu, Jinhong Deng, Xinchen Gao, Wen Li, Lixin Duan. 2021

92 citations recorded by the source corpus.

Existing cross-domain semantic segmentation methods usually focus on the overall segmentation results of whole objects but neglect the importance of object boundaries. In this work, we find that the segmentation performance can be considerably boosted if we treat object boundaries properly. For that, we propose a novel method called BAPA-Net, which is based on a convolutional neural network via Boundary Adaptation and Prototype Alignment, under the unsupervised domain adaptation setting. Specifically, we first construct additional images by pasting objects from source images to target images, and we develop a so-called boundary adaptation module to weigh each pixel based on its distance to the nearest boundary pixel of those pasted source objects. Moreover, we propose another prototype alignment module to reduce the domain mismatch by minimizing distances between the class prototypes of the source and target domains, where boundaries are removed to avoid domain confusion during prototype calculation. By integrating the boundary adaptation and prototype alignment, we are able to train a discriminative and domain-invariant model for cross-domain semantic segmentation. We conduct extensive experiments on the benchmark datasets of urban scenes (i.e., GTA5→Cityscapes and SYNTHIA→Cityscapes). And the promising results clearly show the effectiveness of our BAPA-Net method over existing state-of-the-art for cross-domain semantic segmentation. Our implementation is available at https://github.com/manmanjun/BAPA-Net.

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

1. Wen Li
2. Yahao Liu
3. Jinhong Deng
4. Lixin Duan
5. Tong Chu
6. Zhen Fang
7. Jiale Tao
8. Xiao Wang

In Computer Vision and Pattern Recognition

1. Wen Li
2. Yahao Liu
3. Jinhong Deng
4. Lixin Duan
5. Tong Chu
6. Zhen Fang
7. Jiale Tao
8. Xiao Wang

Citations in the corpus

• Federated Class-Incremental Learning (2022, background): “[34] integrates unsupervised domain adaptation [5, 9, 27, 28, 57] into federated learning framework [14, 31].”
• Denoised Maximum Classifier Discrepancy for Source-Free Unsupervised Domain Adaptation (2022, methodology): “In addition to the inter-domain alignment method, some methods consider intra-domain alignment (Pan et al. 2020) or fit the target distribution in a straightforward manner (Wang and Breckon 2020; Liu et al. 2021).”
• HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation (2022, unknown): “To put this into context, the training of other UDA methods [10, 24, 25] can take several days.”
• Undoing the Damage of Label Shift for Cross-domain Semantic Segmentation (2022, methodology): “Recently, selfsupervised methods, including self-training [16, 17, 32, 49, 51, 52, 54, 55] and semantic consistency [26, 41, 47], have been shown to significantly improve the cross-domain semantic segmentation performance.”