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

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

From Air to Wear: Personalized 3D Digital Fashion With AR/VR Immersive 3D Sketching.

IEEE transactions on visualization and computer graphics·2025

Same author

LLaFS++: Few-Shot Image Segmentation With Large Language Models.

IEEE transactions on pattern analysis and machine intelligence·2025

Same author

Not Every Patch is Needed: Towards a More Efficient and Effective Backbone for Video-based Person Re-identification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2025

Same author

Learning Social Spatio-Temporal Relation Graph in the Wild and a Video Benchmark.

IEEE transactions on neural networks and learning systems·2021

Same author

IPGN: Interactiveness Proposal Graph Network for Human-Object Interaction Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2021

Same author

Cycloaddition Reaction of Vinylphenylfurans and Dimethyl Acetylenedicarboxylate to [8 + 2] Isomers via Tandem [4 + 2]/Diradical Alkene-Alkene Coupling/[1,3]-H Shift Reactions: Experimental Exploration and DFT Understanding of Reaction Mechanisms.

The Journal of organic chemistry·2016

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

Search research articles

Related Experiment Video

Updated: May 24, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Structural and Statistical Texture Knowledge Distillation and Learning for Segmentation.

Deyi Ji, Feng Zhao, Hongtao Lu

IEEE Transactions on Pattern Analysis and Machine Intelligence

|March 3, 2025

Summary

This summary is machine-generated.

This study introduces a new framework for semantic segmentation that effectively combines structural and statistical texture knowledge. The proposed methods enhance deep networks by leveraging low-level texture details for improved performance on benchmark datasets.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: May 24, 2025

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Computer Vision
Machine Learning
Image Processing

Background:

High-level deep features often overlook crucial low-level texture information, impacting semantic segmentation accuracy.
Local structural patterns and global statistical properties (e.g., smoothness, contrast) are vital for detailed image characterization.

Purpose of the Study:

To re-emphasize and integrate low-level texture information into deep networks for semantic segmentation.
To propose a novel framework for structural and statistical texture knowledge distillation (SSTKD).

Main Methods:

Introduced Contourlet Decomposition Module (CDM) to extract structural texture knowledge.
Developed Texture Intensity Equalization Module (TIEM) and Quantization Congruence Loss (QDL) for statistical texture knowledge.
Proposed Co-occurrence TIEM (C-TIEM) and enhanced segmentation frameworks (STLNet++, U-SSNet).

Main Results:

Demonstrated significant effectiveness of the proposed methods across three semantic segmentation tasks.
Achieved state-of-the-art performance on seven popular benchmark datasets.
Validated the ability of existing networks to better utilize texture information.

Conclusions:

The SSTKD framework successfully integrates structural and statistical texture knowledge into deep networks.
The proposed modules and frameworks offer a robust approach to improving semantic segmentation.
Low-level texture features are essential for achieving high performance in complex segmentation tasks.