• Home
  • Search
  • DPNet: Dual-Path Network for Real-Time Object Detection With Lightweight Attention.
  • Open Access IconOpen Access
  • Cite Icon53
  • https://doi.org/10.1109/tnnls.2024.3376563Copy DOI Icon

DPNet: Dual-Path Network for Real-Time Object Detection With Lightweight Attention.

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

The recent advances in compressing high-accuracy convolutional neural networks (CNNs) have witnessed remarkable progress in real-time object detection. To accelerate detection speed, lightweight detectors always have few convolution layers using a single-path backbone. Single-path architecture, however, involves continuous pooling and downsampling operations, always resulting in coarse and inaccurate feature maps that are disadvantageous to locate objects. On the other hand, due to limited network capacity, recent lightweight networks are often weak in representing large-scale visual data. To address these problems, we present a dual-path network, named DPNet, with a lightweight attention scheme for real-time object detection. The dual-path architecture enables us to extract in parallel high-level semantic features and low-level object details. Although DPNet has a nearly duplicated shape with respect to single-path detectors, the computational costs and model size are not significantly increased. To enhance representation capability, a lightweight self-correlation module (LSCM) is designed to capture global interactions, with only a few computational overheads and network parameters. In the neck, LSCM is extended into a lightweight cross correlation module (LCCM), capturing mutual dependencies among neighboring scale features. We have conducted exhaustive experiments on MS COCO, Pascal VOC 2007, and ImageNet datasets. The experimental results demonstrate that DPNet achieves a state-of-the-art trade off between detection accuracy and implementation efficiency. More specifically, DPNet achieves 31.3% AP on MS COCO test-dev, 82.7% mAP on Pascal VOC 2007 test set, and 41.6% mAP on ImageNet validation set, together with nearly 2.5M model size, 1.04 GFLOPs, and 164 and 196 frames/s (FPS) FPS for input images of three datasets.

Similar Papers
  • Research Article

Design of a Hardware-Optimized High-Performance CNN Accelerator for Real-Time Object Detection Using YOLOv3 with Darknet-19 Architecture

  • Mar 18, 2026
  • Electronics
  • Shuo Wu +2
  • Research Article
  • Citations1

Lightweight Network for Real-Time Object Detection in Fisheye Cameras

  • Jan 01, 2025
  • Laser & Optoelectronics Progress
  • 王新蕾 Wang Xinlei +3
  • Conference Article
  • Citations6

On the study of predictors in Single Shot Multibox Detector

  • Dec 27, 2017
  • Xuemei Xie +4
  • Book Chapter
  • Citations5

Real-time Detection of Tiny Objects Based on a Weighted Bi-directional FPN

  • Jan 01, 2022
  • Yaxuan Hu +2
  • Research Article

REAL-TIME OBJECT DETECTION OF SIMPLE DRAWINGS USING YOLO11 ON CONSTRAINED DATASETS

  • Mar 05, 2025
  • MM Science Journal
  • Ladislav Hric +2
  • PDF
  • Research Article
  • Citations20

A Real-Time 3-Dimensional Object Detection Based Human Action Recognition Model

  • Jan 01, 2024
  • IEEE Open Journal of the Computer Society
  • Chhaya Gupta +6
  • Research Article
  • Citations7

A Real-Time Object Detection Processor With xnor-Based Variable-Precision Computing Unit

  • Jun 01, 2023
  • IEEE Transactions on Very Large Scale Integration (VLSI) Systems
  • Wonjae Lee +4
  • Research Article

Real-Time Object Detection and Tracking in Video Streams Using Deep Learning

  • Feb 26, 2026
  • International Journal of Scientific Research in Engineering and Management
  • Sreeshylam Rasula
  • Research Article
  • Citations102

Real-Time Object Detection With Reduced Region Proposal Network via Multi-Feature Concatenation.

  • Aug 21, 2019
  • IEEE Transactions on Neural Networks and Learning Systems
  • Kuan-Hung Shih +3
  • Research Article

ADVANCED SENSOR ARRAY TECHNIQUES FOR REAL-TIME DETECTION OF APPROACHING OBJECTS AND PERSONS

  • Apr 15, 2025
  • International Journal of Environmental Sciences
  • Kassem Al-Attabi
  • PDF
  • Research Article
  • Citations45

Design and implementation of real-time object detection system based on single-shoot detector and OpenCV.

  • Nov 02, 2022
  • Frontiers in Psychology
  • Fazal Wahab +5
  • Research Article
  • Citations10

Mixed Stage Partial Network and Background Data Augmentation for Surveillance Object Detection

  • Dec 01, 2022
  • IEEE Transactions on Intelligent Transportation Systems
  • Ping-Yang Chen +3
  • PDF
  • Research Article
  • Citations38

An Approach on Image Processing of Deep Learning Based on Improved SSD

  • Mar 17, 2021
  • Symmetry
  • Liang Jin +1
  • Research Article

Research On Traffic Sign Detection Based on Transformer and Yolov5

  • Mar 13, 2024
  • Highlights in Science, Engineering and Technology
  • Zhonghao Xie
  • Conference Article
  • Citations2

Exploiting the ACCuracy-ACCeleration tradeoff: VINS-assisted real-time object detection on moving systems

  • Jun 24, 2019
  • Betty Le Dem +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.