• Home
  • Search
  • AKSeg: combining variable kernel convolution with Nash multi task learning
  • https://doi.org/10.1093/comjnl/bxaf135Copy DOI Icon

AKSeg: combining variable kernel convolution with Nash multi task learning

Show More
  • Abstract
  • Literature Map
  • References
  • Similar Papers
Abstract

Abstract In complex image multi-task learning, the precision and effectiveness of feature extraction are often constrained by traditional convolutional methods, including issues with scale invariance and difficulties in feature sharing across tasks. To tackle these challenges, we introduce a straightforward but efficient model called AKSeg. AKSeg effectively combines Adaptive Kernel Convolution (AKConv) with a Nash-based multi-task learning strategy within the SegNet framework, improving the model’s ability to capture multi-task features from images. First, AKSeg incorporates AKConv into the encoder layer of the SegNet. By dynamically adjusting the size and shape of convolutional kernels, AKSeg can accurately capture features of various scales from images. Then, a Nash game strategy is employed in the AKSeg to update parameters and weights as tasks change. To tackle challenges like feature extraction across varying tasks and improve multi-task learning capability, AKSeg utilizes multiple channels to efficiently extract distinct features for each task. Additionally, AKSeg addresses the issue of dead Rectified Linear Unit (ReLU) by eliminating inactive neurons through the use of Leaky Rectified Linear Unit (LeakyReLU). Extensive experimental results demonstrate that the AKSeg outperforms baseline methods remarkably. Specifically, AKSeg reduces the loss value by 4.48%, improves mIoU by 4.52%, and increases pixel accuracy by 1.73%. These results validate the usefulness of AKSeg in enhancing image multi-task learning performance.

Similar Papers
  • Research Article
  • Citations1

Three-Dimensional Magnetotelluric Forward Modeling Using Multi-Task Deep Learning with Branch Point Selection

  • Feb 19, 2025
  • Remote Sensing
  • Fei Deng +3
  • Research Article
  • Citations23

Multi-task feature selection with sparse regularization to extract common and task-specific features

  • Feb 22, 2019
  • Neurocomputing
  • Jiashuai Zhang +3
  • Research Article

AI FRAMEWORK FOR PREDICTING PHYSIOLOGICAL INDICATORS FROM HIGH-RESOLUTION IRIS IMAGES IN PARKINSON’S DISEASE PATIENTS

  • Oct 22, 2025
  • Journal of Mechanics in Medicine and Biology
  • Hakwon Kim +5
  • Research Article
  • Citations16

Robust texture analysis of multi-modal images using Local Structure Preserving Ranklet and multi-task learning for breast tumor diagnosis

  • Feb 09, 2017
  • Neurocomputing
  • Xiaoming Xi +7
  • Research Article

Accurate Iris Segmentation for Non-Cooperative Iris Recognition through Multi-task Network

  • Jul 21, 2022
  • YMER Digital
  • Pradeep Kumar
  • Conference Article
  • Citations4

Multi Task Learning for Plant Leaf Segmentation and Counting

  • Jan 23, 2023
  • Bharathi Chaudhury +3
  • Conference Article
  • Citations3

Recognizing Emotions evoked by Movies using Multitask Learning

  • Sep 28, 2021
  • Hassan Hayat +2
  • Research Article

Noise processing and multitask learning for far‐field dialect classification

  • Aug 10, 2022
  • Concurrency and Computation: Practice and Experience
  • Hai Wang +6
  • Conference Article
  • Citations51

Joint Prediction of Multiple Vulnerability Characteristics Through Multi-Task Learning

  • Nov 01, 2019
  • Xi Gong +4
  • Research Article
  • Citations91

Joint Modeling of Heterogeneous Sensing Data for Depression Assessment via Multi-task Learning

  • Mar 26, 2018
  • Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
  • Jin Lu +9
  • Research Article
  • Citations18

Dual feature correlation guided multi-task learning for Alzheimer's disease prediction

  • Dec 01, 2021
  • Computers in Biology and Medicine
  • Shanshan Tang +4
  • Research Article

MBLKNet: a large kernel convolution-driven network with multi-task self-supervised learning for SAR maritime target classification

  • Nov 28, 2025
  • Geo-spatial Information Science
  • Shuang Yang +10
  • Conference Article
  • Citations7

Prototype Feature Extraction for Multi-task Learning

  • Apr 25, 2022
  • Shen Xin +7
  • Research Article
  • Citations12

Glaucoma detection from retinal fundus images using graph convolution based multi-task model

  • Mar 01, 2025
  • e-Prime - Advances in Electrical Engineering, Electronics and Energy
  • Satyabrata Lenka +2
  • Research Article

Multi-Focus Image Fusion Algorithm Based on Multi-Task Learning and PS-ViT

  • Nov 01, 2024
  • IEICE Transactions on Information and Systems
  • Qinghua Wu +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.