Decoupling Makes Weakly Supervised Local Feature Better

Kunhong Li, Longguang Wang, Li Liu, Qing Ran, Kai Xu, Yulan Guo; Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022, pp. 15838-15848

Weakly supervised learning can help local feature methods to overcome the obstacle of acquiring a large-scale dataset with densely labeled correspondences. However, since weak supervision cannot distinguish the losses caused by the detection and description steps, directly conducting weakly supervised learning within a joint training describe-then-detect pipeline suffers limited performance. In this paper, we propose a decoupled training describe-then-detect pipeline tailored for weakly supervised local feature learning. Within our pipeline, the detection step is decoupled from the description step and postponed until discriminative and robust descriptors are learned. In addition, we introduce a line-to-window search strategy to explicitly use the camera pose information for better descriptor learning. Extensive experiments show that our method, namely PoSFeat (Camera Pose Supervised Feature), outperforms previous fully and weakly supervised methods and achieves state-ofthe-art performance on a wide range of downstream tasks.