Real-time unknown object detection by using only high-level image features with Grounding DINO 1.5
Real-time unknown object detection by using only high-level image features with Grounding DINO 1.5
Grounding DINO 1.5: Advance the “Edge” of Open-Set Object Detection
arXiv paper abstract https://arxiv.org/abs/2405.10300
arXiv PDF paper https://arxiv.org/pdf/2405.10300
GitHub https://github.com/IDEA-Research/Grounding-DINO-1.5-API
… introduces Grounding DINO 1.5 … open-set object detection models developed by IDEA Research, which aims to advance the “Edge” of open-set object detection.
… two models: Grounding DINO 1.5 Pro, a high-performance model … for stronger generalization … across … scenarios, and Grounding DINO 1.5 Edge …optimized for faster speed … in … edge deployment.
… DINO 1.5 Pro model advances … by scaling up the model architecture, integrating an enhanced vision backbone, and expanding the training dataset to over 20 million images with grounding annotations, thereby achieving a richer semantic understanding.
The Grounding DINO 1.5 Edge model, while designed for efficiency with reduced feature scales, maintains robust detection … by being trained on the same comprehensive dataset.
… DINO 1.5 Pro … attaining a 54.3 AP on the COCO detection benchmark and a 55.7 AP on the LVIS-minival zero-shot transfer benchmark, setting new records for … object detection.
… DINO 1.5 Edge model … optimized with TensorRT, achieves a speed of 75.2 FPS while attaining a zero-shot performance of 36.2 AP on the LVIS-minival benchmark …
Stay up to date. Subscribe to my posts https://morrislee1234.wixsite.com/website/contact
Web site with my other posts by category https://morrislee1234.wixsite.com/website
LinkedIn https://www.linkedin.com/in/morris-lee-47877b7b
