wanghao9610/OV-DINO
A unified open-vocabulary detection model that detects and segments objects based on free-form text descriptions using language-aware selective fusion.
Not currently ranked — collecting fresh signals.
star history
OV-DINO is a foundation model designed for open-vocabulary detection and segmentation tasks. It employs language-aware selective fusion to enable zero-shot object detection, meaning it can detect and segment object categories it has never seen during training based on textual descriptions. The model achieves state-of-the-art results on benchmarks like MS COCO and LVIS for zero-shot object detection.
Frequently asked
- What is wanghao9610/OV-DINO?
- A unified open-vocabulary detection model that detects and segments objects based on free-form text descriptions using language-aware selective fusion.
- Is OV-DINO open source?
- Yes — wanghao9610/OV-DINO is open source, released under the Apache-2.0 license.
- What language is OV-DINO written in?
- wanghao9610/OV-DINO is primarily written in Python.
- How popular is OV-DINO?
- wanghao9610/OV-DINO has 406 stars on GitHub.
- Where can I find OV-DINO?
- wanghao9610/OV-DINO is on GitHub at https://github.com/wanghao9610/OV-DINO.