Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Feb 22, 2026

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

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

Published on: December 15, 2023

S-CNN: Subcategory-Aware Convolutional Networks for Object Detection.

Tao Chen, Shijian Lu, Jiayuan Fan

IEEE Transactions on Pattern Analysis and Machine Intelligence

|September 30, 2017

Summary

This summary is machine-generated.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Corrigendum to "Investigating the enhancement mechanism of cellulose enzymatic hydrolysis: Machine learning-assisted acidic deep eutectic solvent pretreatment" [Int. J. Biol. Macromol. 368 (2026)152724 (13 pages)].

International journal of biological macromolecules·2026

Same author

Investigating the enhancement mechanism of cellulose enzymatic hydrolysis: Machine learning-assisted acidic deep eutectic solvent pretreatment.

International journal of biological macromolecules·2026

Same author

Advances in Leaching Agents for Indirect CO<sub>2</sub> Mineralization.

ACS omega·2026

Same author

Research on the Preparation of Carbon-Negative Backfill Materials via Enhanced Carbon Sequestration Using Coal-Based Solid Waste.

ACS omega·2026

Same author

Synergistic Enhancement of Photocatalytic H<sub>2</sub>O<sub>2</sub> Production over Carbon Nitride Oxide/Biochar Composites.

Molecules (Basel, Switzerland)·2025

Same author

Identification of Critical Risk Factors in Carbon Capture and Storage (CCS) Projects.

Risk analysis : an official publication of the Society for Risk Analysis·2025

Same journal

Relation DETR+: Exploring Explicit Position Relation Prior for Dense Prediction.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

RBF++: Quantifying and Optimizing Reasoning Boundaries across Measurable and Unmeasurable Capabilities for Chain-of-Thought Reasoning.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

CAFE: Cross-View Adaptive Fusion and Cluster Center Enhancement for Robust Multi-View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

DIVER: Reinforced Diffusion Breaks Imitation Bottlenecks in End-to-End Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Ethics-Aware Safe Reinforcement Learning for Rare-Event Risk Control in Interactive Urban Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Learning Shape Anchors for Holistic Indoor Scene Understanding.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

This study introduces a subcategory-aware Convolutional Neural Network (S-CNN) to improve object detection by addressing intra-class variations. The S-CNN method enhances accuracy in identifying objects with diverse appearances.

Area of Science:

Computer Vision
Machine Learning
Artificial Intelligence

Background:

Deep Convolutional Neural Networks (CNNs) combined with region proposals have advanced object detection.
However, significant intra-class variation and object deformation hinder the performance of current CNN-based object detection systems.

Purpose of the Study:

To address the challenge of intra-class variation in object detection.
To propose a novel Subcategory-aware CNN (S-CNN) framework to enhance object detection accuracy.

Main Methods:

Automatic grouping of training samples into subcategories using instance sharing maximum margin clustering.
Training a multi-component Aggregated Channel Feature (ACF) detector to generate latent training samples for each subcategory.
Utilizing an iterative learning algorithm for joint optimization of subcategorization, ACF detector, and the S-CNN classifier.

More Related Videos

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Related Experiment Videos

Last Updated: Feb 22, 2026

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

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

Published on: December 15, 2023

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

Feeding latent samples and subcategory labels into the CNN classifier to refine object detection by filtering false proposals.

Main Results:

The proposed S-CNN technique effectively handles intra-class variation and object deformation.
Experiments on standard datasets (INRIA Person, Pascal VOC 2007, MS COCO) demonstrate superior performance compared to state-of-the-art methods.
The method significantly improves generic object detection capabilities.

Conclusions:

The S-CNN framework offers a robust solution for improving object detection accuracy, particularly in scenarios with high intra-class variability.
This approach advances the field of computer vision by enabling more precise and reliable object identification.