---
title: IDEA-Research/grounding-dino-base
description: "The Grounding DINO model was proposed in Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection by Shilong L. Swin, 233M parameters."
canonical_url: https://superlinked.com/models/idea-research-grounding-dino-base
last_updated: 2026-05-24
---

# IDEA-Research/grounding-dino-base

The Grounding DINO model was proposed in Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection by Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang.

Source: [IDEA-Research/grounding-dino-base on HuggingFace](https://huggingface.co/IDEA-Research/grounding-dino-base)

## Overview

| Field | Value |
|-------|-------|
| Architecture | Swin |
| Parameters | 233M |
| Tasks | Extract |
| Outputs | Bounding Boxes |
| License | apache-2.0 |
| Inputs | text, image |

## Benchmarks

### COCO

Domain: general · Task: detection · Language: en

Object detection on COCO natural images

Corpus: 5,000 · Queries: 5,000

**Variant: default_limit-1000**

**Performance (A10G b1 c4):** Detect 0.0 mpix/s · Detect p50 33.0s

**Performance (L4-SPOT b1 c4):** Detect 0.8 mpix/s · Detect p50 785.8ms

**Variant: default_limit-100**

**Quality:** ap: 0.5809 · ap50: 0.7349 · ap75: 0.6241 · ar 100: 0.6503

**Performance (RTX-4090 b1 c16):** Detect 3.4 mpix/s · Detect p50 670.9ms

[Reference](https://cocodataset.org/)