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 Concept Videos

Visual System01:26

Visual System

658
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...
658
Association Areas of the Cortex01:21

Association Areas of the Cortex

6.0K
Association areas are regions of the cerebral cortex that do not have a specific sensory or motor function. Instead, they integrate and interpret information from various sources to enable higher cognitive processes such as memory, learning, and decision-making. Some key association areas include the following:
Prefrontal Association Area: This area is located in the frontal lobe and is involved in planning, decision-making, and moderating social behavior. It connects with primary motor areas,...
6.0K
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)01:15

Insensitive Nuclei Enhanced by Polarization Transfer (INEPT)

469
Insensitive Nuclei Enhanced by Polarization Transfer (INEPT) is an advanced Nuclear Magnetic Resonance (NMR) technique specifically designed to detect and enhance the signals of low-abundance nuclei, such as carbon-13 and nitrogen-15, in small molecules. The fundamental principle behind INEPT is the transfer of polarization from a more abundant and highly polarizable nucleus, typically hydrogen-1, to the low-abundance nucleus of interest. This process effectively boosts the NMR signal of the...
469
Classification of Systems-I01:26

Classification of Systems-I

281
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
281
Classification of Systems-II01:31

Classification of Systems-II

219
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
219
Force Classification01:22

Force Classification

1.4K
Forces play a crucial role in the study of physics and engineering. They are essential in describing the motion, behavior, and equilibrium of objects in the physical world. Forces can be classified based on their origin, type, and direction of action.
Contact and non-contact forces are two of the most widely used categories of forces. As the name suggests, contact forces require physical contact between two objects to act upon each other. Examples of contact forces include frictional,...
1.4K

You might also read

Related Articles

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

Sort by
Same author

Dietary Sodium-Potassium Ratio in Low-Sodium Diet Population and Its Association with Stroke: Insights from NHANES Database.

Neuro endocrinology letters·2025
Same author

A commentary on 'comparative effectiveness of acupoint stimulation for preventing postoperative nausea and vomiting after general anesthesia: a network meta-analysis of randomized trials'.

International journal of surgery (London, England)·2025
Same author

Integrated mRNA sequence optimization using deep learning.

Briefings in bioinformatics·2023
Same author

Acupuncture at ST36 Alleviates the Behavioral Disorder of Autistic Rats by Inhibiting TXNIP-Mediated Activation of NLRP3.

Journal of neuropathology and experimental neurology·2022
Same author

Codon optimization with deep learning to enhance protein expression.

Scientific reports·2020
Same author

Capsule Networks Showed Excellent Performance in the Classification of hERG Blockers/Nonblockers.

Frontiers in pharmacology·2020
Same journal

Exploiting audio-visual modalities in videos: Object detection via multi-stage bilateral coupling network.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Reliability-aware modality completion with cross-modal distillation for federated learning with missing modalities.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

IGFD-Net: Illumination-guided frequency decoupling for polarization image fusion.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Multiple-Strategies dung beetle optimizer and its applications in engineering optimization and bankruptcy prediction.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Aggregating global-scale pixel-wise forgery cues within a graph.

Neural networks : the official journal of the International Neural Network Society·2026
Same journal

Finite-Time intermittent control for secure synchronization of Neutral-Type stochastic delayed neural networks under aperiodic DoS attacks.

Neural networks : the official journal of the International Neural Network Society·2026
See all related articles

Related Experiment Video

Updated: Aug 28, 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

614

AFINet: Attentive Feature Integration Networks for image classification.

Xinglin Pan1, Jing Xu2, Yu Pan3

  • 1University of Electronic Science and Technology of China, Chengdu, China; Department of Network Intelligence, Peng Cheng Lab, Shenzhen, China.

Neural Networks : the Official Journal of the International Neural Network Society
|September 17, 2022
PubMed
Summary
This summary is machine-generated.

Attentive Feature Integration (AFI) modules enhance residual networks by improving feature utilization and reducing redundancy. AFI-Nets offer better performance and efficiency compared to standard ResNets, as demonstrated on the ImageNet dataset.

Keywords:
AttentionCNNFeature integrationImage classification

More Related Videos

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

957

Related Experiment Videos

Last Updated: Aug 28, 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

614
Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.3K
Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization
05:49

Author Spotlight: Advancing CBCT and Digital Dental Image Integration with AI-Assisted Digitization

Published on: February 23, 2024

957

Area of Science:

  • Computer Vision
  • Deep Learning
  • Artificial Intelligence

Background:

  • Convolutional Neural Networks (CNNs) excel in image classification.
  • Residual networks (ResNets) use skip connections to combat vanishing gradients.
  • Existing skip connections limit intermediate feature utilization due to simple iterative updates.

Purpose of the Study:

  • To mitigate redundancy in residual-like networks.
  • To introduce Attentive Feature Integration (AFI) modules for enhanced feature utilization.
  • To develop new AFI-Net architectures.

Main Methods:

  • Designed Attentive Feature Integration (AFI) modules.
  • Integrated AFI modules into residual-like network architectures, creating AFI-Nets.
  • Evaluated AFI-ResNet-152 on the ImageNet dataset.

Main Results:

  • AFI-ResNet-152 achieved a 1.24% relative improvement on ImageNet.
  • FLOPs were reduced by approximately 10%.
  • The number of parameters decreased by about 9.2% compared to ResNet-152.

Conclusions:

  • AFI modules effectively model correlations between different feature levels.
  • AFI-Nets selectively transfer features with minimal overhead.
  • AFI-Nets represent a more efficient and performant evolution of residual networks.