AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection

Shilong Liu, Zhaoyang Zeng, Tianhe Ren, Feng Li, Hao Zhang, Jie Yang, Qing Jiang, Chunyuan Li, Jianwei Yang, Hang Su, Jun Zhu, Lei Zhang

ECCV 2024 · Detection and segmentation › Open-set and few-shot detection · approach: Open-vocabulary object detection · 2,472 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add encoder (neck) cross-modality fusion (ablation)Grounding DINO T · LVIS minivalAP: 13.1 -> 16.1Improved
use language-guided query selection instead of static (ablation)Grounding DINO T · LVIS minivalAP: 13.6 -> 16.1Improved
add text cross-attention in decoder (ablation)Grounding DINO T · LVIS minivalAP: 14.3 -> 16.1Improved
use sub-sentence text prompt instead of word-level (ablation)Grounding DINO T · LVIS minivalAP: 15.6 -> 16.1Improved
language-guided query selection and sub-sentence prompt on COCO fine-tune (ablation)Grounding DINO T · COCO minival fine-tuneAP: 56.6 -> 56.9 (query selection), 56.6 -> 56.9 (sub-sentence)No clear effect
add grounding data GoldG to pre-trainingGrounding DINO T · COCO zero-shotAP: 46.7 -> 48.1Improved
add caption data Cap4M to pre-trainingGrounding DINO T · LVIS minival zero-shotAP: 25.6 -> 27.4Improved
add RefCOCO/+/g to pre-trainingGrounding DINO T · LVIS minivalAP: 25.6 -> 21.9Hurt
add RefCOCO/+/g to pre-trainingGrounding DINO T · ODinW zero-shotAP: 20.0 -> 17.7Hurt
add COCO data to pre-trainingGrounding DINO T · COCO minivalAP: 48.5 -> 56.1Improved
add COCO data to pre-trainingGrounding DINO T · ODinW zero-shotAP: 17.7 -> 17.4Hurt
enlarge input images by 1.5xGrounding DINO L · COCO fine-tuneAP: 62.6 -> 63.0No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy