Plugging Self-Supervised Monocular Depth Into Unsupervised Domain Adaptation for Semantic Segmentation

Adriano Cardace, Luca De Luigi, Pierluigi Zama Ramirez, Samuele Salti, Luigi Di Stefano; Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV), 2022, pp. 1129-1139

Abstract


Although recent semantic segmentation methods have made remarkable progress, they still rely on large amounts of annotated training data, which are often infeasible to collect in the autonomous driving scenario. Previous works usually tackle this issue with Unsupervised Domain Adaptation (UDA), which entails training a network on synthetic images and applying the model to real ones while minimizing the discrepancy between the two domains. Yet, these techniques do not consider additional information that may be obtained from other tasks. Differently, we propose to exploit self-supervised monocular depth estimation to improve UDA for semantic segmentation. On one hand, we deploy depth to realize a plug-in component which can inject complementary geometric cues into any existing UDA method. We further rely on depth to generate a large and varied set of samples to Self-Train the final model. Our whole proposal allows for achieving state-of-the-art performance (58.8 mIoU) in the GTA5->CS benchmark benchmark. Code is available at https://github.com/CVLAB-Unibo/d4-dbst.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Cardace_2022_WACV, author = {Cardace, Adriano and De Luigi, Luca and Ramirez, Pierluigi Zama and Salti, Samuele and Di Stefano, Luigi}, title = {Plugging Self-Supervised Monocular Depth Into Unsupervised Domain Adaptation for Semantic Segmentation}, booktitle = {Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision (WACV)}, month = {January}, year = {2022}, pages = {1129-1139} }