2026-09-18T22:36:52Zhttps://iris.unitn.it/oai/request

oai:iris.unitn.it:11572/4818522026-04-29T13:56:22Zcom_11572_237821com_11572_101871col_11572_237822ou_ou00002

Generalizing Under Data Scarcity. Enhancing the representation capability from few samples. Braccaioli, Lorenzo co-supervisor: Chiara Corridori Braccaioli, Lorenzo Conci, Nicola few-shot learning meta-learning in-context learning industrial anomaly detection The widespread adoption of deep learning in both research and industrial contexts has revealed a central limitation: many real-world applications lack large, diverse, and reliably labeled datasets. This challenge is particularly evident in domains where data acquisition is costly, error-prone, or inherently scarce, such as industrial inspection, anomaly detection and localization. This thesis investigates how learning systems can be designed to operate effectively when only a small number of samples are available at training or inference time. The first part of the thesis focuses on meta-learning transformers for supervised and unsupervised few-shot tasks. We explore how transformers behave when trained on structured, multi-domain datasets under controlled conditions, where train/test contamination can be explicitly avoided. By reframing few-shot learning as a sequence modeling problem, we analyze the generalization capabilities of in-context learners across domains, and study how training order influences performance. We propose the GEOM framework for supervised few-shot classification and extend its principles to the unsupervised setting with CAMeLU, demonstrating state-of-the-art performance in cross-domain scenarios. The second part of the thesis addresses the gap between academic research and real-world industrial constraints. Working with an Italian company specializing in glass inspection systems, we propose two domain-specific solutions. The first is a few-shot approach for structural glass defect classification, enabling flexible adaptation to new defect types and variations in glass materials. The second is a reconstruction-based anomaly detection pipeline for identifying irregularities in silk-screen printed patterns, where labeled data are extremely scarce. This dissertation highlights the importance of designing models that do not rely on large-scale datasets, but instead leverage task structure, adaptation mechanisms, and data-efficient learning strategies. By bridging foundational research on meta-learning with concrete industrial use cases, the thesis demonstrates that few-shot paradigms can be robust, scalable, and practically applicable in demanding environments. 2026-04-15 info:eu-repo/semantics/doctoralThesis https://hdl.handle.net/11572/481852 eng firstpage:1 lastpage:140 numberofpages:140 info:eu-repo/semantics/embargoedAccess alleditors:co-supervisor: Chiara Corridori Università degli studi di Trento place:TRENTO license:Tutti i diritti riservati (All rights reserved) license uri:iris.PRI01