Learning from Small Data in Computer Vision

Dear Colleagues,

This Special Issue is associated with the International Workshop on Learning from Small Data in Computer Vision, held in conjunction with the Asian Conference on Computer Vision (ACCV 2026), which will take place from December 14–18, 2026, in Osaka, Japan. For more information about the conference and the workshop, please visit the following link: https://accv2026.org/.

We invite researchers and practitioners from academia and industry to submit their latest original research, review articles, and short communications to this Special Issue. Learning effectively from limited labeled data remains a fundamental bottleneck in computer vision. While large-scale benchmarks have driven substantial progress, numerous real-world applications—ranging from autonomous driving and robotic vision to medical imaging, industrial inspection, and remote sensing—cannot rely on massive annotated datasets due to prohibitive annotation costs, privacy regulations, data scarcity, or the inherent rarity of target events. This challenge has motivated a rich spectrum of data-efficient paradigms, including few-shot and meta-learning, transfer learning, data augmentation, synthetic generation, active learning, semi-supervised and self-supervised learning, and knowledge-guided approaches.

This Special Issue seeks to consolidate recent advances in data-efficient visual learning, bridging the gap between cutting-edge algorithmic development and practical deployment under real-world constraints such as domain shift, noisy labels, imbalanced classes, and dynamic environments. Topics of interest include, but are not limited to:

• Few-shot, zero-shot, and meta-learning for vision;
• Data augmentation and synthetic image generation (GANs, diffusion models, physics-based rendering);
• Transfer learning, domain adaptation, and fine-tuning of foundation models;
• Active learning and optimal query strategies;
• Semi-supervised and self-supervised representation learning;
• In-context learning and dynamic model adaptation;
• Knowledge-guided vision (incorporating 3D geometry, physical laws, and scene constraints);
• Robustness, generalization, and uncertainty quantification;
• Federated and privacy-preserving learning for vision;
• Real-world applications in robotics, medical imaging, autonomous systems, and remote sensing.

All submissions will undergo a rigorous peer-review process to ensure high quality, novelty, and relevance to the theme of small-data learning in computer vision. This Special Issue aims to foster collaboration and knowledge exchange among researchers, engineers, and domain experts, ultimately advancing the frontier of data-efficient visual intelligence.

We look forward to your valuable contributions.

Dr. Alaa Tharwat Othman
Prof. Dr. Essam A. Rashed
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 250 words) can be sent to the Editorial Office for assessment.

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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Machine Learning and Knowledge Extraction 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 1800 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.

• few-shot learning
• active learning
• semi-supervised learning
• data augmentation
• diffusion models
• transfer learning
• foundation models