Try OV-DINO, a more powerful open-vocabulary detector.

[wanghao9610]

trafficstars

Thanks for the awesome YOLO-World, I share our recent work 🦖OV-DINO: Unified Open-Vocabulary Detection with Language-Aware Selective Fusion.

• OV-DINO is a novel unified open vocabulary detection approach that offers superior performance and effectiveness for practical real-world application.

• OV-DINO entails a Unified Data Integration pipeline that integrates diverse data sources for end-to-end pre-training, and a Language-Aware Selective Fusion module to improve the vision-language understanding of the model.

• OV-DINO shows significant performance improvement on COCO and LVIS benchmarks compared to previous methods, achieving relative improvements of +5.5% AP on COCO and +4.7% AP on LVIS compared to YOLO-World in zero-shot evaluation.

We have released the evaluation, fine-tuning, demo code in our project, feel free to try our model for your application.

Project: https://wanghao9610.github.io/OV-DINO

Paper: https://arxiv.org/abs/2407.07844

Code: https://github.com/wanghao9610/OV-DINO

Demo: http://47.115.200.157:7860

Welcome everyone to try our model and feel free to raise issue if you encounter any problem.

[ForestWang]

how about the inference time compared with yolo-world?

[wanghao9610]

@ForestWang We haven't tested the inference time systematically, the inference time is already fast according to the demo without any deployment optimization.