CORTEXA
← Browse
crossrefMachine Learning and Knowledge Extraction2022-01-14Cited by 64

A Transfer Learning Evaluation of Deep Neural Networks for Image Classification

Nermeen Abou Baker, Nico Zengeler, Uwe Handmann

Transfer learning is a machine learning technique that uses previously acquired knowledge from a source domain to enhance learning in a target domain by reusing learned weights. This technique is ubiquitous because of its great advantages in achieving high performance while saving training time, memory, and effort in network design. In this paper, we investigate how to select the best pre-trained model that meets the target domain requirements for image classification tasks. In our study, we refined the output layers and general network parameters to apply the knowledge of eleven image processing models, pre-trained on ImageNet, to five different target domain datasets. We measured the accuracy, accuracy density, training time, and model size to evaluate the pre-trained models both in training sessions in one episode and with ten episodes.

View free PDFSource page

Related papers

crossrefMachine Learning and Knowledge Extraction2025-10-13Cited by 2

Learning to Partition: Dynamic Deep Neural Network Model Partitioning for Edge-Assisted Low-Latency Video Analytics

Yan Lyu, Likai Liu, Xuezhi Wang, Zhiyu Fan, Jinchen Wang, Guanyu Gao

In edge-assisted low-latency video analytics, a critical challenge is balancing on-device inference latency against the high bandwidth costs and network delays of offloading. Ineffectively managing this trade-off degrades performance and hinders critical applications like autonom…

View free PDFSource page
crossrefMachine Learning and Knowledge Extraction2026-06-16

Edge-Optimized Deep and Transfer Learning for Efficient DDoS Detection in IIoT Networks

Mikiyas Alemayehu, Mohamed Chahine Ghanem, Hamza Kheddar

The increasing convergence of Operational Technology (OT) and Information Technology (IT) within the Industrial Internet of Things (IIoT) brings about remarkable improvements in monitoring and automation. However, it also exposes industrial systems to large-scale Distributed Deni…

View free PDFSource page
crossrefMachine Learning and Knowledge Extraction2026-07-23

From Black Box to Clarity: A Systematic Review of Explainability Methods in Deep Convolutional Neural Networks

Zina Tayari, Mourad Zaied

Deep neural networks (DNNs) have significantly advanced machine perception and reasoning; however, their lack of transparency in decision-making continues to pose a major challenge, particularly in high-stakes domains such as healthcare, finance, and law. This is especially conce…

View free PDFSource page
crossrefMachine Learning and Knowledge Extraction2025-11-28Cited by 1

Time Series-to-Image Encoding for Classification Using Convolutional Neural Networks: A Novel and Robust Approach

Hammoud Al Joumaa, Loui Al-Shrouf, Mohieddine Jelali

In recent decades, data collection technologies have evolved to facilitate the monitoring and improvement of numerous activities and processes in everyday human life. Their evolution is propelled by the advancement of artificial intelligence (AI), which aims to emulate human inte…

View free PDFSource page
crossrefMachine Learning and Knowledge Extraction2026-06-25

Autism Spectrum Disorder Detection Using a Weighted-Average Ensemble of Deep Convolutional Neural Networks on Eye-Tracking Images

Masroor Ahmed, Sadam Hussain, Ivan Amaya, José Carlos Ortiz-Bayliss

Autism Spectrum Disorder is a long-term neurodevelopmental disorder. Early diagnosis is crucial for timely rehabilitation and intervention. Recently, machine learning and deep learning techniques have been widely explored and have produced encouraging results using eye-tracking s…

View free PDFSource page
crossrefMachine Learning and Knowledge Extraction2025-03-30Cited by 2

RoSe-Mix: Robust and Secure Deep Neural Network Watermarking in Black-Box Settings via Image Mixup

Tamara El Hajjar, Mohammed Lansari, Reda Bellafqira, Gouenou Coatrieux, Katarzyna Kapusta, Kassem Kallas

Due to their considerable costs, deep neural networks (DNNs) are valuable assets that need to be protected in terms of intellectual property (IP). From this statement, DNN watermarking gains significant interest since it allows DNN owners to prove their ownership. Various methods…

View free PDFSource page