Dual-Path Autoencoder-DenseNet Architecture for Robust Object Classification via Background-Free Reconstruction and Multi-Task Feature Fusion

Object classification in real-world environments is often challenged by image degradation such as noise, blur, and poor lighting, which degrades the performance of conventional deep learning models. To address this, we propose a multi-task dual-path autoencoder-DenseNet framework that simultaneously...

Full description

Bibliographic Details

Published in:	2025 International Conference on Artificial Intelligence and Digital Ethics (ICAIDE) pp. 458 - 463
Main Authors:	Rosli, Hashim, Ali, Rozniza, Hitam, Muhamad Suzuri, Deris, Ashanira Mat
Format:	Conference Proceeding
Language:	English
Published:	IEEE 29.05.2025
Subjects:	autoencoder Autoencoders component Feature extraction Image reconstruction loss function Mean square error methods multi-task Multitasking Noise object classification Pipelines Root mean square Service robots Visualization
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!