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."
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.
Stars
67
Forks
3
Language
Python
License
—
Category
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.
Higher-rated alternatives
BR-IDL/PaddleViT
:robot: PaddleViT: State-of-the-art Visual Transformer and MLP Models for PaddlePaddle 2.0+
pathak22/unsupervised-video
[CVPR 2017] Unsupervised deep learning using unlabelled videos on the web
IBM/CrossViT
Official implementation of CrossViT. https://arxiv.org/abs/2103.14899
NVlabs/GCVit
[ICML 2023] Official PyTorch implementation of Global Context Vision Transformers
ViTAE-Transformer/ViTDet
Unofficial implementation for [ECCV'22] "Exploring Plain Vision Transformer Backbones for Object...