DiffYOLO: Object Detection for Anti-Noise via YOLO and Diffusion Models

TL;DR

DiffYOLO enhances YOLO object detection models by integrating diffusion models to improve performance on noisy and low-quality datasets without retraining from scratch.

Contribution

The paper introduces DiffYOLO, a novel framework that leverages diffusion models to enhance YOLO's robustness to noisy data, enabling effective detection without extensive retraining.

Findings

Improved detection accuracy on noisy datasets

Maintains high performance on high-quality datasets

Framework adaptable to various datasets and architectures

Abstract

Object detection models represented by YOLO series have been widely used and have achieved great results on the high quality datasets, but not all the working conditions are ideal. To settle down the problem of locating targets on low quality datasets, the existing methods either train a new object detection network, or need a large collection of low-quality datasets to train. However, we propose a framework in this paper and apply it on the YOLO models called DiffYOLO. Specifically, we extract feature maps from the denoising diffusion probabilistic models to enhance the well-trained models, which allows us fine-tune YOLO on high-quality datasets and test on low-quality datasets. The results proved this framework can not only prove the performance on noisy datasets, but also prove the detection results on high-quality test datasets. We will supplement more experiments later (with various datasets and network architectures).