wjun0830/Difficulty-Aware-Simulator

Official PyTorch Repository of "Difficulty-Aware Simulator for Open Set Recognition" (ECCV 2022 Paper)

31
/ 100
Emerging

This project helps machine learning researchers evaluate and improve models designed to recognize known objects while also identifying completely new, unknown objects they haven't seen before. It takes a dataset of images and a trained open-set recognition model, then outputs performance metrics like F1 score and AUROC to show how well the model handles both familiar and unfamiliar categories. It's for researchers and developers working on advanced computer vision systems.

No commits in the last 6 months.

Use this if you are a machine learning researcher developing computer vision models that need to accurately classify known categories while simultaneously detecting and rejecting images belonging to novel, previously unseen categories.

Not ideal if you are looking for a pre-trained, ready-to-deploy open-set recognition system for a specific application, rather than a tool for research and evaluation.

open-set-recognition computer-vision machine-learning-research model-evaluation image-classification
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 16 / 25
Community 7 / 25

How are scores calculated?

Stars

43

Forks

3

Language

Python

License

MIT

Last pushed

Jul 28, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/wjun0830/Difficulty-Aware-Simulator"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.