Learning from limited labelled data: contributions to weak, few-shot, and unsupervised learning

• Autores: Julio José Silva Rodríguez
• Directores de la Tesis: Ricardo Insa Franco (dir. tes.), Pablo Salvador Zuriaga (dir. tes.), Valeriana Naranjo Ornedo (dir. tes.)
• Lectura: En la Universitat Politècnica de València ( España ) en 2022
• Idioma: español
• Tribunal Calificador de la Tesis: Antonio José Albiol Colomer (presid.), Luz García Martínez (secret.), Beatriz Marcotegui (voc.)
• Programa de doctorado: Programa de Doctorado en Telecomunicación por la Universitat Politècnica de València
• Materias:
  • Matemáticas
    • Ciencia de los ordenadores
      • Inteligencia artificial
• Enlaces
  • Tesis en acceso abierto en: RiuNet
• Resumen

  • In the last decade, deep learning (DL) has become the main tool for computer vision (CV) tasks. Under the standard supervised learnng paradigm, and thanks to the progressive collection of large datasets, DL has reached impressive results on different CV applications using convolutional neural networks (CNNs). Nevertheless, CNNs performance drops when sufficient data is unavailable, which creates challenging scenarios in CV applications where only few training samples are available, or when labeling images is a costly task, that require expert knowledge. Those scenarios motivate the research of not-so-supervised learning strategies to develop DL solutions on CV.

    In this thesis, we have explored different less-supervised learning paradigms on different applications. Concretely, we first propose novel self-supervised learning strategies on weakly supervised classification of gigapixel histology images. Then, we study the use of contrastive learning on few-shot learning scenarios for automatic railway crossing surveying. Finally, brain lesion segmentation is studied in the context of unsupervised anomaly segmentation, using only healthy samples during training. Along this thesis, we pay special attention to the incorporation of tasks-specific prior knowledge during model training, which may be easily obtained, but which can substantially improve the results in less-supervised scenarios. In particular, we introduce relative class proportions in weakly supervised learning in the form of inequality constraints. Also, attention homogenization in VAEs for anomaly localization is incorporated using size and entropy regularization terms, to make the CNN to focus on all patterns for normal samples. The different methods are compared, when possible, with their supervised counterparts.

    In short, different not-so-supervised DL methods for CV are presented along this thesis, with substantial contributions that promote the use of DL in data-limited scenarios. The obtained results are promising, and provide researchers with new tools that could avoid annotating massive amounts of data in a fully supervised manner.