Li Liu, Kai Xu, Kunhong Li, Longguang Wang, Yulan Guo, Qing Ran
We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
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 describethen-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 task.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2201.02861")
get_code_for_paper("2201.02861")
have("2201.02861")
The run record, dated, one paper per request, free:
curl https://syntology.ai/api/ran/2201.02861.json
A badge for a README (the split and the date, never a ratio):
[](https://syntology.ai/paper/2201.02861)
Connect an agent — have() is free.