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 Videos

Exploiting Cross-Task Synergy via Frequency-Driven Hierarchical Learning for Multi-Task Dense Prediction.

Yunzhi Zhuge, Xinzhuo Yu, Lu Zhang

IEEE Transactions on Image Processing : a Publication of the IEEE Signal Processing Society

|May 28, 2026

Summary

This summary is machine-generated.

Related Concept Videos

Associative Learning

Associative Learning

Associative learning is a fundamental concept in behavioral psychology, wherein a connection is established between two stimuli or events, leading to a learned response. This process is critical in understanding how behaviors are acquired and modified. Conditioning, the mechanism through which associations are formed, can be divided into two main types: classical conditioning and operant conditioning, each elucidating different aspects of associative learning.
Classical conditioning, also known...

Multi-input and Multi-variable systems

Multi-input and Multi-variable systems

Cruise control systems in cars are designed as multi-input systems to maintain a driver's desired speed while compensating for external disturbances such as changes in terrain. The block diagram for a cruise control system typically includes two main inputs: the desired speed set by the driver and any external disturbances, such as the incline of the road. By adjusting the engine throttle, the system maintains the vehicle's speed as close to the desired value as possible.
In the absence of...

You might also read

Related Articles

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

Sort by

Same author

DiMuS: Disentangled Multi-Signal Learning for Weakly Supervised Point-based 3D Object Detection.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Visual-Textual Information-Driven Tactile Data Generation Method.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Class Sensitive Calibration and Discrepancy-Aware Synthesis for Semi-Supervised Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2026

Same author

Diffusion-based cross-staining feature transformation for whole slide image analysis: From H&E to IHC representation learning.

Medical image analysis·2026

Same author

SD-ReID: View-Aware Stable Diffusion for Aerial-Ground Person Re-Identification.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same author

Context-Infused Trajectories: Enhancing Context and Frame Consistency in Reasoning Video Object Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

CLASH-CTTA: Class-Wise Shift-Aware Hierarchical Continual Test-Time Adaptation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Voxel-based Point Cloud Geometry Compression with Space-to-Channel Context.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

RIGI: Rectifying Image-to-3D Generation Inconsistency via Uncertainty-aware Learning.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

DA-Cal: Towards Cross-Domain Calibration in Semantic Segmentation.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Multi-Dimensional Quality Assessment for Single-Image-to-3D Contents: Dataset and Model.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

Same journal

Enhancing Underwater Light Field Images via Global Geometry-aware Diffusion Process.

IEEE transactions on image processing : a publication of the IEEE Signal Processing Society·2026

See all related articles

This study introduces the Hierarchical Frequency-Adaptive Network (HiFAN) to improve multi-task dense prediction by using frequency-domain analysis for better feature learning and detail preservation across tasks.

Area of Science:

Computer Vision
Machine Learning
Deep Learning

Background:

Multi-task dense prediction enhances pixel-level performance through shared representations and inter-task collaboration.
Existing methods struggle with multi-scale feature fusion and detail preservation due to implicit task relationships and neglect of frequency-domain cues.

Purpose of the Study:

To propose a novel hierarchical frequency-driven framework, the Hierarchical Frequency-Adaptive Network (HiFAN), for improved multi-task dense prediction.
To address challenges in multi-scale feature fusion, task interaction, and accurate decoding by incorporating frequency-domain analysis.

Main Methods:

Designed a task-adaptive fusion module leveraging multi-scale frequency information to enhance spatial details via dynamic convolutional kernels.
Introduced an efficient cross-task interaction module using low-frequency representations for global context exchange.

Related Experiment Videos

Developed a high-frequency-aware decoder to mitigate feature smoothing and detail loss in Transformer-based architectures.

Main Results:

HiFAN demonstrated effectiveness on PASCAL-Context and NYUD-v2 benchmarks.
Achieved strong and competitive performance across multiple dense prediction tasks.

Conclusions:

The proposed HiFAN framework successfully enhances multi-task dense prediction by effectively utilizing frequency-domain information.
HiFAN offers a robust solution for cross-task collaborative optimization, improving feature learning and detail preservation.