DiffusionEngine: Diffusion model is scalable data engine for object detection

doi:10.1016/j.patcog.2025.112141

DiffusionEngine: Diffusion model is scalable data engine for object detection

2025-07-16

0

PRE

AI

DOI：10.1016/j.patcog.2025.112141

Original

Original request for help

Save

Abstract

En 中文

Data is the cornerstone of deep learning. This paper reveals that the recently-developed Diffusion Model is a scalable data engine for object detection. Existing methods for scaling up detection-oriented data often require manual collection or generative models to obtain target images, followed by data augmentation and labeling to produce training pairs, which are costly, complex, or lacking diversity. To address these issues, we present DiffusionEngine (DE), a data scaling-up engine that provides high-quality detection-oriented training pairs in a single stage. DE consists of a pre-trained diffusion model and an effective Detection-Adapter, contributing to generating scalable, diverse and generalizable detection data in a plug-and-play manner. Detection-Adapter is learned to align the implicit semantic and location knowledge in off-the-shelf diffusion models with detection-aware signals to make better bounding-box predictions. Additionally, we contribute two datasets, i.e., COCO-DE and VOC-DE, to scale up existing detection benchmarks for facilitating follow-up research. Extensive experiments demonstrate that data scaling-up via DE can achieve significant improvements in diverse scenarios, such as various detection algorithms, self-supervised pre-training, data-sparse, label-scarce, cross-domain, and semi-supervised learning. For example, when using DE with a DINO-based adapter to scaling-up data, mAP is improved by 3.1 % on COCO, 7.6 % on VOC and 11.5 % on Clipart.

Keywords:

Diffusion Model

Object Detection

Data Scaling-Up

Detection-Adapter

Generative Models

DiffusionEngine: Diffusion model is scalable data engine for object detection

Abstract

Journal

Organization

Cited Papers