www.icact.org

Member Login

TACT Journal Homepage

Call for Paper

Committee

Find My Paper

Author Homepage

Statistics & History

Welcome Message

Paper Procedure

FAQ

Paper Archives

Outstanding Papers

Program & Proceedings

Presentation Platform

Hotel & Travel Info

Photo Gallery

Scheduler Login

Seminar

Archives Login

Sponsors

Virual Oral Question and Answer


IEEE/ICACT20250193 Question.1 Questioner: haun620@kyonggi.ac.kr 2025-02-17 오후 1:28:00	IEEE/ICACT20250193 Answer.1 Answer by Auhor arifulislamro@gmail.com 2025-02-17 오후 1:28:00
What dataset was the 'transfer learning model' trained on before fintuning?	Before fine-tuning, the transfer learning models (Inception, Xception, VGG19, and ResNet50) were pre-trained on large-scale image datasets, typically ImageNet. ImageNet is a widely used dataset with millions of labeled images across thousands of categories, enabling models to learn general image features. During fine-tuning for skin cancer detection, the models were adapted to the ISIC 2018 dataset, refining their weights for distinguishing between malignant and benign lesions. So, the transfer learning models were initially trained on ImageNet before being fine-tuned on the ISIC 2018 dataset.

Select Voice