DINO-X: A Unified Vision Model for Open-World Object Detection and
  Understanding

Tianhe Ren; Yihao Chen; Qing Jiang; Zhaoyang Zeng; Yuda Xiong; Wenlong Liu; Zhengyu Ma; Junyi Shen; Yuan Gao; Xiaoke Jiang; Xingyu Chen; Zhuheng Song; Yuhong Zhang; Hongjie Huang; Han Gao; Shilong Liu; Hao Zhang; Feng Li; Kent Yu; Lei Zhang

Paper · arXiv 2411.14347

DINO-X: A Unified Vision Model for Open-World Object Detection and Understanding

Tianhe Ren, Yihao Chen, Qing Jiang, Zhaoyang Zeng, Yuda Xiong, Wenlong Liu, Zhengyu Ma, Junyi Shen, Yuan Gao, Xiaoke Jiang, Xingyu Chen, Zhuheng Song, Yuhong Zhang, Hongjie Huang, Han Gao, Shilong Liu, Hao Zhang, Feng Li, Kent Yu, Lei Zhang

18 upvotesNovember 21, 2024arXiv 预印本

AI 摘要

DINO-X, a Transformer-based object-centric vision model, achieves top performance in open-world object detection through flexible prompts, a large-scale dataset, and integration of multiple perception tasks.

Transformer-based encoder-decoder architectureopen-world object detectiontext promptvisual promptuniversal object promptlarge-scale datasetGrounding-100Mopen-vocabulary detectionobject-level representationdetectionsegmentationpose estimationobject captioningobject-based QAzero-shot object detectionlong-tailed objects

Abstract

In this paper, we introduce DINO-X, which is a unified object-centric vision model developed by IDEA Research with the best open-world object detection performance to date. DINO-X employs the same Transformer-based encoder-decoder architecture as Grounding DINO 1.5 to pursue an object-level representation for open-world object understanding. To make long-tailed object detection easy, DINO-X extends its input options to support text prompt, visual prompt, and customized prompt. With such flexible prompt options, we develop a universal object prompt to support prompt-free open-world detection, making it possible to detect anything in an image without requiring users to provide any prompt. To enhance the model's core grounding capability, we have constructed a large-scale dataset with over 100 million high-quality grounding samples, referred to as Grounding-100M, for advancing the model's open-vocabulary detection performance. Pre-training on such a large-scale grounding dataset leads to a foundational object-level representation, which enables DINO-X to integrate multiple perception heads to simultaneously support multiple object perception and understanding tasks, including detection, segmentation, pose estimation, object captioning, object-based QA, etc. Experimental results demonstrate the superior performance of DINO-X. Specifically, the DINO-X Pro model achieves 56.0 AP, 59.8 AP, and 52.4 AP on the COCO, LVIS-minival, and LVIS-val zero-shot object detection benchmarks, respectively. Notably, it scores 63.3 AP and 56.5 AP on the rare classes of LVIS-minival and LVIS-val benchmarks, both improving the previous SOTA performance by 5.8 AP. Such a result underscores its significantly improved capacity for recognizing long-tailed objects.