Skip to Content

Journal of Imaging, Volume 8, Issue 9

2022 September - 29 articles

Cover Story: Today, it is common to compare different tools for a certain task, such as segmentation or classification. What is the best way to compare them, however? This is especially important in the context of AI with many loss functions, optimisers and a plethora of architectures. This work presents a comparison framework, which is applied for the classification of Computed Tomography images of individuals with COVID-19, pneumonia or disease-free. Five architectures (ResNet-50, ResNet-50r, DenseNet-121, MobileNet-v3 and the state-of-the-art CaiT-24-XXS-224), Adam and AdamW optimisers, cross entropy and weighted cross entropy were combined to form 20 experiments with 10 repetitions and then bootstrapped for 1000 cycles. Performance was compared using the Friedman–Nemenyi non-parametric statistical test. View this paper
  • Issues are regarded as officially published after their release is announced to the table of contents alert mailing list .
  • You may sign up for email alerts to receive table of contents of newly released issues.
  • PDF is the official format for papers published in both, html and pdf forms. To view the papers in pdf format, click on the "PDF Full-text" link, and use the free Adobe Reader to open them.

Articles

There are no articles in this issue yet.

Get Alerted

Add your email address to receive forthcoming issues of this journal.

XFacebookLinkedIn
J. Imaging - ISSN 2313-433X