Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Nov 16, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

780

Adaptively Dense Feature Pyramid Network for Object Detection.

Haodong Pan1, Guangfeng Chen1, Jue Jiang2

  • 1College of Mechanical Engineering, Donghua University, Shanghai 201620, China.

IEEE Access : Practical Innovations, Open Solutions
|February 22, 2021
PubMed
Summary

We introduce the Adaptively Dense Feature Pyramid Network (ADFPNet), a novel object detection system for identifying objects at various scales. This method achieves state-of-the-art accuracy on benchmark datasets, enabling efficient real-time detection.

Related Concept Videos

Visual System01:26

Visual System

1.4K
Light enters the eye through the cornea, a transparent, dome-shaped surface covering the surface of the eyeball that helps to direct and focus incoming light. This light is then channeled toward the pupil, an adjustable opening whose size is controlled by the iris. The iris, a pigmented muscle, regulates the amount of light entering the eye by contracting or dilating the pupil, thereby ensuring optimal light levels for clear vision.
Once through the pupil, the light passes through the lens, a...
1.4K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

LEARNABLE HIERARCHICAL VISUAL CONTEXTS FOR TUMOR SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGES.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

MHub.ai: A Standardized Platform for Reproducible AI Research in Medical Imaging.

Research square·2026
Same author

Segmentation regularized training for multi-domain deep learning registration applied to magnetic resonance-guided prostate cancer radiotherapy.

Physics and imaging in radiation oncology·2026
Same author

Co-distilled attention guided masked image modeling with noisy teacher for self-supervised learning on medical images.

Proceedings of machine learning research·2026
Same author

AsyCMST: Asymmetric cross-modal spatio-temporal learning for multimodal ultrasound nodule recognition.

Medical image analysis·2026
Same author

CD8+ T cells in Hashimoto's thyroiditis-associated papillary thyroid carcinoma.

European thyroid journal·2026

Area of Science:

  • Computer Vision
  • Deep Learning
  • Object Detection

Background:

  • Object detection networks often struggle with objects across diverse scales.
  • Existing methods may not efficiently capture rich semantic information for accurate detection.

Purpose of the Study:

  • To propose a novel one-stage object detection network, ADFPNet, capable of detecting objects across various scales.
  • To enhance the Single Shot Multibox Detector (SSD) framework with a new module for improved feature representation.

Main Methods:

  • Developed the Adaptively Dense Feature Pyramid Network (ADFPNet) based on the SSD framework.
  • Introduced the ADFP module, comprising a Dense Multi-scales and Receptive Fields Block (DMSRB) and an Adaptive Feature Calibration Block (AFCB).
  • Utilized atrous convolutions in DMSRB for dense feature extraction and AFCB for feature calibration.
Keywords:
SSDDenseNetSENetatrous convolutionobject detection

Related Experiment Videos

Last Updated: Nov 16, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

780

Main Results:

  • Achieved state-of-the-art accuracy with mAP of 82.5 on VOC 2007 and 36.4 on MS COCO test-dev set using a VGG-16 backbone.
  • Demonstrated real-time detection capabilities with an mAP of 81.1 and 62.5 FPS on VOC 2007 at 300x300 resolution.
  • The proposed ADFPNet effectively handles objects across a wide range of scales.

Conclusions:

  • ADFPNet offers a significant advancement in one-stage object detection.
  • The novel ADFP module enhances feature representation, leading to superior accuracy and efficiency.
  • The network meets real-time detection requirements, making it suitable for practical applications.