Towards Label-free Learning for Industrial Vision Applications

Dear Colleagues,

Recent trends in machine learning and computer vision technology have effectively boosted the application of industrial visual inspection. However, most of the available systems work in a human-in-the-loop manner and still require hand-crafted labels for training supervised AI models. In order to take a step forwards, there is a need to reduce manual intervention and automatic incremental iterative AI models for a complex production system.

We are pleased to invite you to publish theoretical advancements about label-free machine learning manners on a variety of topics, including unsupervised learning, self-supervised learning, semi-supervised learning, weakly supervised learning, few-shot learning, incremental learning, and transfer learning. Furthermore, the latest strides in computer vision have the potential to be applied in a variety of domains. We also invite you to publish novel practical developments, especially on anomaly detection, intrusion detection, hand pose estimation, pose estimation, video surveillance monitoring, medical imaging diagnostics, industrial manufacturing applications, and software tools for label-free machine learning.

This Special Issue aims to promote high-quality and original research papers on the above-described areas. Topics of interest include, without being limited to:

• Label-free machine learning manners without human-in-the-loop.
• Software tools on label-free learning for industrial vision application.
• Unsupervised, semi-supervised, self-supervised, and weakly supervised learning methods.
• Transfer, low-shot, few-shot, incremental, continual, and long-tailed learning methods.
• Two/three-dimensional anomaly detection; video intrusion detection applications.
• Video surveillance monitoring; human pose estimation applications.
• Ultrasound/X-ray/MRI imaging-assisted medical or industrial diagnostics.
• Production system automation and incremental iterative learning.

Dr. Jiawei Li
Dr. Naiqi Li
Dr. Ognjen Arandjelović
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Information is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• machine learning
• deep learning
• computer vision
• unsupervised learning
• self-supervised learning
• industrial anomaly detection
• video signal processing
• medical imaging diagnostics