‘Hide-and-Seek’ Random Masking Transform
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 17.9k
- Forks
- 7.3k
- Avg merge
- 1d 15h
- Merged PRs (30d)
- 13
Description
🚀 The feature
Source
Hide-and-Seek: Forcing a Network to be Meticulous for Weakly-supervised Object and Action Localization (Scholar, Arxiv)
Number of citations: 542
Method
The image is divided into a grid and then every patch of this grid is masked with probability p. So the inputs are patch_size, p and fill_value.
Motivation, pitch
Like described in the paper, this augmentation method can improve weakly-supervised object localization, as with it not only the most discriminative parts in the image are found, but all relevant ones.
I have already implemented this method, so I could open a PR, if you think this feature is a useful addition.
Alternatives
No response
Additional context
Here an example from the paper.
cc @vfdev-5 @datumbox
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
No file or test is named in the issue. Start by reading the repository's existing image-transform entry points and the linked Hide-and-Seek paper, then compare the proposed patch_size, p, and fill_value behavior with current transform conventions. Done means the transform is integrated consistently and its masking behavior is covered by the repository's tests.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- computer-vision, machine-learning
- Issue type
- Feature
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Mostly clear
- Newbie friendliness
- 38/100