https://github.com/y-t-g/hua_rs

Hierarchical Uncertainty Aggregation (Park et al., 2022) in Rust.
https://github.com/y-t-g/hua_rs

active-learning pyo3 python rust

Last synced: about 1 month ago
JSON representation

Hierarchical Uncertainty Aggregation (Park et al., 2022) in Rust.

• Host: GitHub
• URL: https://github.com/y-t-g/hua_rs
• Owner: Y-T-G
• License: mit
• Created: 2024-01-22T08:22:26.000Z (over 1 year ago)
• Default Branch: main
• Last Pushed: 2025-02-11T08:23:12.000Z (4 months ago)
• Last Synced: 2025-03-13T12:47:31.378Z (3 months ago)
• Topics: active-learning, pyo3, python, rust
• Language: Rust
• Homepage:
• Size: 15.6 KB
• Stars: 1
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

        
# Hierarchical Uncertainty Aggregation

This repo implements hierarchical uncertainty aggregation from the paper _Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation_ by Park et al. (2022).

It is in written in Rust with bindings for Python.

## Build

Run `maturin build` to build the wheel.

## Usage

1. Import the package with `import hua`.

2. Create a `hua.HUA` object with `iou_threshold` and `score_threshold`.

3. Call `hua.HUA.run()` with:

    ```text

    bounding_boxes: Array of bounding boxes in the format [x1, y1, x2, y2] of shape (N, 4),

    class_probabilities: Array of class probabilities of shape (N, C),

    uncertainty_scores: Array of instance level uncertainty scores of shape (N,),

    scales: Array of FPN scales from which the corresponding prediction was obtained of shape (N,).

    ```

4. The method returns the informativeness score of the image and the indices of the groups created by HUA.

## Acknowledgements

[Powerboxes](https://github.com/Smirkey/powerboxes): It was used to speed up the IOU calculation in the code.