Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection

Recent advancements in object detection, particularly with DiffusionDet, have demonstrated impressive performance. However, its reliance on numerous random noise-based object candidates limits its efficiency. To overcome this limitation, we propose DifAda, a novel object detection model that incorpo...

Full description

Saved in:
Bibliographic Details
Main Authors: Xingyu Zou, Kaixu Han, Xinle Zhang, Wenhao Wang, Ning Wu
Format: Article
Language:English
Published: MDPI AG 2024-12-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/23/11367
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850260154786775040
author Xingyu Zou
Kaixu Han
Xinle Zhang
Wenhao Wang
Ning Wu
author_facet Xingyu Zou
Kaixu Han
Xinle Zhang
Wenhao Wang
Ning Wu
author_sort Xingyu Zou
collection DOAJ
description Recent advancements in object detection, particularly with DiffusionDet, have demonstrated impressive performance. However, its reliance on numerous random noise-based object candidates limits its efficiency. To overcome this limitation, we propose DifAda, a novel object detection model that incorporates adaptive noise into the diffusion framework. DifAda employs an adaptive noise mechanism that blends random noise with latent codes, enhancing object candidate utilization and improving object localization. Our model features a simplified decoder structure by employing a single decoder layer and utilizes an adaptive interaction mechanism to further refine feature representations, leading to improved performance with fewer parameters. In addition, DifAda supports flexible speed–accuracy trade-offs through adjustable sampling and iteration steps, requiring no retraining. Experimental results across multiple benchmarks, including COCO and RUOD, demonstrate that DifAda achieves competitive performance with significantly fewer object candidates and parameters. Our findings suggest that DifAda represents a step forward in efficient and scalable object detection.
format Article
id doaj-art-6962d7b24aab46fc98da749167a8348a
institution OA Journals
issn 2076-3417
language English
publishDate 2024-12-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-6962d7b24aab46fc98da749167a8348a2025-08-20T01:55:41ZengMDPI AGApplied Sciences2076-34172024-12-0114231136710.3390/app142311367Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object DetectionXingyu Zou0Kaixu Han1Xinle Zhang2Wenhao Wang3Ning Wu4School of Computer, Electronics and Information, Guangxi University, Nanning 530004, ChinaGuangxi Key Laboratory of Ocean Engineering Equipment and Technology, Beibu Gulf University, Qinzhou 535011, ChinaCollege of Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, ChinaCollege of Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, ChinaCollege of Naval Architecture and Ocean Engineering, Beibu Gulf University, Qinzhou 535011, ChinaRecent advancements in object detection, particularly with DiffusionDet, have demonstrated impressive performance. However, its reliance on numerous random noise-based object candidates limits its efficiency. To overcome this limitation, we propose DifAda, a novel object detection model that incorporates adaptive noise into the diffusion framework. DifAda employs an adaptive noise mechanism that blends random noise with latent codes, enhancing object candidate utilization and improving object localization. Our model features a simplified decoder structure by employing a single decoder layer and utilizes an adaptive interaction mechanism to further refine feature representations, leading to improved performance with fewer parameters. In addition, DifAda supports flexible speed–accuracy trade-offs through adjustable sampling and iteration steps, requiring no retraining. Experimental results across multiple benchmarks, including COCO and RUOD, demonstrate that DifAda achieves competitive performance with significantly fewer object candidates and parameters. Our findings suggest that DifAda represents a step forward in efficient and scalable object detection.https://www.mdpi.com/2076-3417/14/23/11367object detectiondiffusion modelneural network
spellingShingle Xingyu Zou
Kaixu Han
Xinle Zhang
Wenhao Wang
Ning Wu
Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
Applied Sciences
object detection
diffusion model
neural network
title Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
title_full Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
title_fullStr Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
title_full_unstemmed Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
title_short Adaptive Noise-Powered Diffusion Model for Efficient and Accurate Object Detection
title_sort adaptive noise powered diffusion model for efficient and accurate object detection
topic object detection
diffusion model
neural network
url https://www.mdpi.com/2076-3417/14/23/11367
work_keys_str_mv AT xingyuzou adaptivenoisepowereddiffusionmodelforefficientandaccurateobjectdetection
AT kaixuhan adaptivenoisepowereddiffusionmodelforefficientandaccurateobjectdetection
AT xinlezhang adaptivenoisepowereddiffusionmodelforefficientandaccurateobjectdetection
AT wenhaowang adaptivenoisepowereddiffusionmodelforefficientandaccurateobjectdetection
AT ningwu adaptivenoisepowereddiffusionmodelforefficientandaccurateobjectdetection