DASGIL: Domain Adaptation for Semantic and Geometric-aware Image-based Localization
This work addresses a key problem in autonomous driving and mobile robotics by improving localization accuracy in varying conditions, though it appears incremental as it builds on existing domain adaptation and multi-task methods.
The paper tackles long-term visual localization under changing environments by proposing a multi-task architecture that fuses geometric and semantic information into multi-scale latent embeddings for image retrieval, achieving state-of-the-art performance on datasets like Extended CMU-Seasons and Oxford RobotCar.
Long-Term visual localization under changing environments is a challenging problem in autonomous driving and mobile robotics due to season, illumination variance, etc. Image retrieval for localization is an efficient and effective solution to the problem. In this paper, we propose a novel multi-task architecture to fuse the geometric and semantic information into the multi-scale latent embedding representation for visual place recognition. To use the high-quality ground truths without any human effort, the effective multi-scale feature discriminator is proposed for adversarial training to achieve the domain adaptation from synthetic virtual KITTI dataset to real-world KITTI dataset. The proposed approach is validated on the Extended CMU-Seasons dataset and Oxford RobotCar dataset through a series of crucial comparison experiments, where our performance outperforms state-of-the-art baselines for retrieval-based localization and large-scale place recognition under the challenging environment.