Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection
In this paper, we present an open-set object detector, called Grounding DINO, by marrying Transformer-based detector DINO with grounded pre-training, which can detect arbitrary objects with human inputs such as category names or referring expressions. The key solution of open-set object detection is introducing language to a closed-set detector for open-set concept generalization. To effectively fuse language and vision modalities, we conceptually divide a closed-set detector into three phases and propose a tight fusion solution, which includes a feature enhancer, a language-guided query selection, and a cross-modality decoder for cross-modality fusion. While previous works mainly evaluate open-set object detection on novel categories, we propose to also perform evaluations on referring expression comprehension for objects specified with attributes. Grounding DINO performs remarkably well on all three settings, including benchmarks on COCO, LVIS, ODinW, and RefCOCO/+/g. Grounding DINO achieves a $52.5$ AP on the COCO detection zero-shot transfer benchmark, i.e., without any training data from COCO. It sets a new record on the ODinW zero-shot benchmark with a mean $26.1$ AP. Code will be available at \url{https://github.com/IDEA-Research/GroundingDINO}.
PDF AbstractCode
Colab
Spaces
Replicate
Datasets
MS COCO
LVIS
Segmentation in the Wild
Results from the Paper
Ranked #2 on
Zero-Shot Object Detection
on ODinW
(using extra training data)
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Uses Extra Training Data |
Benchmark |
|---|---|---|---|---|---|---|---|
| Object Detection | COCO minival | Grounding DINO | box AP | 63.0 | # 12 | ||
| Object Detection | COCO test-dev | Grounding DINO | box mAP | 63.0 | # 18 | ||
| Zero-Shot Object Detection | LVIS v1.0 minival | GroundingDINO-L | AP | 33.9 | # 8 | ||
| Zero-Shot Object Detection | MSCOCO | Grounding DINO-L (without COCO data) | AP 0.5 | 52.5 | # 3 | ||
| Zero-Shot Object Detection | ODinW | Grounding DINO | Average Score | 26.1 | # 2 | ||
| Object Detection | ODinW Full-Shot 13 Tasks | Grounding DINO | AP | 70.9 | # 4 | ||
| Zero Shot Segmentation | Segmentation in the Wild | Grounded-SAM | Mean AP | 46.0 | # 2 |
