A CONCEPTUAL FRAMEWORK FOR ROBUST FEW-SHOT LEARNING: INTEGRATING UNBALANCED OPTIMAL TRANSPORT AND SELF-SUPERVISED TRANSFORMER REPRESENTATIONS

Hayati Abd Rahman^1* and Pang Yun²

^1*Faculty of Computer and Mathematical Sciences, Universiti Teknologi MARA (UiTM), Shah Alam, Malaysia
^2*Guilin University of Electronic Technology, Beihai, Guangxi, China

^1*This email address is being protected from spambots. You need JavaScript enabled to view it., ²This email address is being protected from spambots. You need JavaScript enabled to view it.



ABSTRACT

Few-shot learning (FSL) aims to enable deep models to generalise from extremely limited labelled data, yet unstable metric matching, distribution imbalances, and weak structural representations in low-data regimes often constrain its performance. This paper proposes a conceptual framework that unifies metric-based similarity learning, Unbalanced Optimal Transport (UOT) via Unbalanced Sinkhorn Distance (USD), and self-supervised Transformer representations to conceptually address the theoretical and structural limitations of existing FSL approaches. The framework theoretically unifies distribution-aware USD matching, SSL-enhanced ViT/Swin feature representations, and metric-based inference within a coherent pipeline. This work aims to provide a theoretical foundation and research roadmap for future empirical studies on robust few-shot learning under realistic, distributionally complex conditions.

Keywords: Few-Shot Learning, Metric Learning, Optimal Transport, Self-Supervised Learning, Sinkhorn Distance, Unbalanced Vision Transformer

Published On: 1 April 2026

 

Full Download