Cross-domain few-shot learning: Theories, methods, and the source-free paradigm

Thesis event information

Date and time of the thesis defence

Place of the thesis defence

Auditorium 101A Palotiesali

Topic of the dissertation

Cross-domain few-shot learning: Theories, methods, and the source-free paradigm

Doctoral candidate

Master of Science Huali Xu

Faculty and unit

University of Oulu Graduate School, Faculty of Information Technology and Electrical Engineering, Center for Machine Vision and Signal Analysis (CMVS)

Subject of study

Computer Science and Engineering

Opponent

Professor Moncef Gabbouj, Tampere University

Custos

Emeritus Professor Olli SilvΓ©n, Center for Machine Vision and Signal Analysis (CMVS)

Add event to calendar

Cross-domain few-shot learning: Theories, methods, and the source-free paradigm

Machine learning degrades under distribution shifts, especially with scarce labels. Cross-domain few-shot learning (CDFSL) aims to generalize to novel classes in unseen domains. This dissertation develops a unified theoretical framework and new recognition methods for CDFSL.

We extend Empirical Risk Minimization to a two-stage optimization that separates intra- and inter-domain challenges, and organize existing methods into four families: 𝓓-Extension (instance-level augmentation), Ξ”-Adaptation (distribution alignment), 𝓗-Constraint (hypothesis-space restriction), and hybrids.

For 𝓓-Extension, we propose Inter-Source Stylization Network (ISSNet), which enriches target instances with styles drawn from unlabeled auxiliary domains, improving generalization via style-driven augmentation.

For Ξ”-Adaptation, we define source-free CDFSL (SF-CDFSL), where source data are inaccessible, and introduce Information-Maximized Distance-aware Contrastive Learning (IM-DCL) to align a pretrained source model with unlabeled target data using distance-aware contrastive learning and information maximization.

For 𝓗-Constraint, we present Step-wise Style Prompt Tuning (StepSPT), which stabilizes learning by constraining the hypothesis space with learnable prompts and step-wise alignment, enabling efficient use of large pretrained models under low-data, source-free conditions.

Overall, the work provides a unified perspective and three complementary methods that enhance robustness and generalization in data-constrained cross-domain scenarios, supporting applications in medical imaging, autonomous systems, and remote sensing.
Created 15.10.2025 | Updated 20.10.2025