Local feature CNNs in models?
Open
Nobody has claimed this yet.
enhancement
needs discussion
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
Hi,
Are the state-of-the-art local patch descriptors welcomed in models? E.g. HardNet https://github.com/DagnyT/hardnet
They are trained in pytorch + torchvision and are potentially useful for low-level vision tasks. However, I understand that they are less transferable than ImageNet-trained ones.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
Start by reviewing the models contribution guidance in the pytorch/vision repository and the linked HardNet project. Determine whether local patch descriptors fit the repository's model scope and contribution expectations; done would be a documented decision about whether and how this model family should be added.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 5/5
- Estimated time
- Over a week
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 20/100