Methods › Computer Vision › Convolutional Neural Networks › ASLFeat
ASLFeat
Introduced by Zixin Luo et al. in ASLFeat: Learning Local Features of Accurate Shape and Localization
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
ASLFeat is a convolutional neural network for learning local features that uses deformable convolutional networks to densely estimate and apply local transformation. It also takes advantage of the inherent feature hierarchy to restore spatial resolution and low-level details for accurate keypoint localization. Finally, it uses a peakiness measurement to relate feature responses and derive more indicative detection scores.
Papers archive 2025-07-28
1 shown of 1, newest first. Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code; it is per sample and not a correctness claim.
-
ASLFeat: Learning Local Features of Accurate Shape and Localization 23 Mar 2020 · 4 repositories · arXiv:2003.10071Syntology ran 0 of 16 samples · 16 unverified
Tasks archive 2025-07-28
2 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
| Task | Papers |
|---|---|
| 3D Reconstruction | 1 |
| Keypoint detection and image matching | 1 |
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections