DIRL: Domain-Invariant Representation Learning for Generalizable Semantic Segmentation

Authors

  • Qi Xu Shanghai Jiao Tong University
  • Liang Yao Tencent YouTu
  • Zhengkai Jiang Tencent YouTu
  • Guannan Jiang CATL
  • Wenqing Chu Tencent YouTu
  • Wenhui Han Fudan University
  • Wei Zhang CATL
  • Chengjie Wang Tencent YouTu
  • Ying Tai Tencent YouTu

DOI:

https://doi.org/10.1609/aaai.v36i3.20193

Keywords:

Computer Vision (CV)

Abstract

Model generalization to the unseen scenes is crucial to real-world applications, such as autonomous driving, which requires robust vision systems. To enhance the model generalization, domain generalization through learning the domain-invariant representation has been widely studied. However, most existing works learn the shared feature space within multi-source domains but ignore the characteristic of the feature itself (e.g., the feature sensitivity to the domain-specific style). Therefore, we propose the Domain-invariant Representation Learning (DIRL) for domain generalization which utilizes the feature sensitivity as the feature prior to guide the enhancement of the model generalization capability. The guidance reflects in two folds: 1) Feature re-calibration that introduces the Prior Guided Attention Module (PGAM) to emphasize the insensitive features and suppress the sensitive features. 2): Feature whiting that proposes the Guided Feature Whiting (GFW) to remove the feature correlations which are sensitive to the domain-specific style. We construct the domain-invariant representation which suppresses the effect of the domain-specific style on the quality and correlation of the features. As a result, our method is simple yet effective, and can enhance the robustness of various backbone networks with little computational cost. Extensive experiments over multiple domains generalizable segmentation tasks show the superiority of our approach to other methods.
AAAI-22 Proceedings Cover

Downloads

Published

2022-06-28

How to Cite

Xu, Q., Yao, L., Jiang, Z., Jiang, G., Chu, W., Han, W., Zhang, W., Wang, C., & Tai, Y. (2022). DIRL: Domain-Invariant Representation Learning for Generalizable Semantic Segmentation. Proceedings of the AAAI Conference on Artificial Intelligence, 36(3), 2884-2892. https://doi.org/10.1609/aaai.v36i3.20193

Issue

Vol. 36 No. 3: AAAI-22 Technical Tracks 3

Section

AAAI Technical Track on Computer Vision III