HRDA: Context-Aware High-Resolution Domain-Adaptive Semantic Segmentation

By Lukas Hoyer, Dengxin Dai, Luc Van Gool. European Conference on Computer Vision, 2022

328 citations recorded by the source corpus.

Unsupervised domain adaptation (UDA) aims to adapt a model trained on the source domain (e.g. synthetic data) to the target domain (e.g. real-world data) without requiring further annotations on the target domain. This work focuses on UDA for semantic segmentation as real-world pixel-wise annotations are particularly expensive to acquire. As UDA methods for semantic segmentation are usually GPU memory intensive, most previous methods operate only on downscaled images. We question this design as low-resolution predictions often fail to preserve fine details. The alternative of training with random crops of high-resolution images alleviates this problem but falls short in capturing long-range, domain-robust context information. Therefore, we propose HRDA, a multi-resolution training approach for UDA, that combines the strengths of small high-resolution crops to preserve fine segmentation details and large low-resolution crops to capture long-range context dependencies with a learned scale attention, while maintaining a manageable GPU memory footprint. HRDA enables adapting small objects and preserving fine segmentation details. It significantly improves the state-of-the-art performance by 5.5 mIoU for GTA-to-Cityscapes and 4.9 mIoU for Synthia-to-Cityscapes, resulting in unprecedented 73.8 and 65.8 mIoU, respectively. The implementation is available at https://github.com/lhoyer/HRDA.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/90f390777d1a23a2c8a4b9b94e29afbf8b76cbd6

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. Chen Change Loy
2. Ziwei Liu
3. Kai Chen
4. Luc Van Gool
5. Jiangmiao Pang
6. Dengxin Dai
7. Lukas Hoyer
8. Wenwei Zhang

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Chen Change Loy
3. Ziwei Liu
4. Ming-Hsuan Yang
5. Xiaogang Wang
6. Dacheng Tao
7. Kai Chen
8. Trevor Darrell

In Radiology, Nuclear Medicine and Imaging

1. Lukas Hoyer
2. Haoran Wang
3. Luc Van Gool
4. Ziwei Liu
5. Dengxin Dai
6. Kai Chen
7. Chen Change Loy

Citations in the corpus

• MIC: Masked Image Consistency for Context-Enhanced Domain Adaptation (2022, methodology): “It is a common strategy used in semi-supervised learning [18,31,82] and UDA [1,32,33,83].”
• Transformer-Based Visual Segmentation: A Survey (2023, background): “Then, HRDA [292] improves DAFormer via a multi-resolution training approach and uses various crops to preserve fine segmentation details and long-range contexts.”