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

TL;DR

Grounding DINO introduces a novel open-set object detection framework that combines Transformer-based detection with grounded pre-training, enabling detection of arbitrary objects using human inputs across multiple benchmarks.

Contribution

The paper proposes a new open-set object detector that integrates language and vision modalities through a tight fusion approach, extending detection capabilities to arbitrary objects and referring expressions.

Findings

Achieves 52.5 AP on COCO zero-shot transfer benchmark.

Sets a new record with 26.1 AP on ODinW zero-shot benchmark.

Performs well on benchmarks including COCO, LVIS, ODinW, and RefCOCO/+/g.

Abstract

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}.