lorebianchi98/FG-OVD

[CVPR 2024 Highlight] Official repository of the paper "The devil is in the fine-grained details: Evaluating open-vocabulary object detectors for fine-grained understanding."

22
/ 100
Experimental

This project helps computer vision researchers and practitioners evaluate and develop object detection models that can recognize fine-grained details in images. It takes an existing dataset like PACO and processes it using a language model to create specialized benchmarks. These benchmarks allow for a deeper understanding of how well models identify subtle object attributes like color or material, not just broad categories. This is for researchers and developers working on advanced image analysis.

No commits in the last 6 months.

Use this if you need to create specialized image datasets to test and improve object detection models' ability to distinguish between very similar objects or recognize subtle visual characteristics.

Not ideal if you are looking for a pre-trained, ready-to-use object detection model without needing to generate custom evaluation datasets.

computer-vision object-detection image-analysis dataset-generation model-evaluation
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 6 / 25

How are scores calculated?

Stars

67

Forks

3

Language

Python

License

Last pushed

Apr 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/lorebianchi98/FG-OVD"

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