[NEW MODEL] Region-based Anomaly Detection

[djdameln]

Description

• This PR adds the model implementation for Region Based Anomaly Detection With Real-Time
  Training and Analysis.
• The classification module was moved to a shared location, so that both DFKDE and RKDE can make use of it.

I've targeted the PR to the datamodules feature branch for now, because this makes it easier to see the changes. Once #822 has been merged, I will re-target this PR to main.

Known Issues

• The feature extractor uses a custom weight file, which is not part of the repo because it's too large. We need to upload this somewhere and load from url.
• No benchmark results available (this is a bit tricky because we don't have proper evaluation metrics for detection models).
• No tiling support.

Examples (UCSDped2)

Changes

• Bug fix (non-breaking change which fixes an issue)
• Refactor (non-breaking change which refactors the code base)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist

• My code follows the pre-commit style and check guidelines of this project.
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing tests pass locally with my changes
• I have added a summary of my changes to the CHANGELOG (not for minor changes, docs and tests).

[ashwinvaidya17]

Thanks