Deep auxiliary learning for visual localization using colorization task
This addresses the problem of reducing annotation costs for visual localization in robotics and autonomous driving, though it is incremental as it builds on existing CNN-based methods with auxiliary tasks.
The paper tackles visual localization for robotics and autonomous driving by proposing an auxiliary learning strategy that uses a self-supervised colorization task to incorporate high-level semantics without manual annotations, resulting in significant accuracy improvements over state-of-the-art methods on indoor and outdoor datasets.
Visual localization is one of the most important components for robotics and autonomous driving. Recently, inspiring results have been shown with CNN-based methods which provide a direct formulation to end-to-end regress 6-DoF absolute pose. Additional information like geometric or semantic constraints is generally introduced to improve performance. Especially, the latter can aggregate high-level semantic information into localization task, but it usually requires enormous manual annotations. To this end, we propose a novel auxiliary learning strategy for camera localization by introducing scene-specific high-level semantics from self-supervised representation learning task. Viewed as a powerful proxy task, image colorization task is chosen as complementary task that outputs pixel-wise color version of grayscale photograph without extra annotations. In our work, feature representations from colorization network are embedded into localization network by design to produce discriminative features for pose regression. Meanwhile an attention mechanism is introduced for the benefit of localization performance. Extensive experiments show that our model significantly improve localization accuracy over state-of-the-arts on both indoor and outdoor datasets.