Centre de documentation
scientifique

Interactions between hierarchical learning and visual system modeling : image classification on small datasets / Thalita Firmo Drumond (2020)  

Public Titre : Interactions between hierarchical learning and visual system modeling : image classification on small datasets Type de document : Thèse/HDR Auteurs : Thalita Firmo Drumond, Auteur ; Frédéric Alexandre, Directeur de thèse ; Thierry Viéville, Directeur de thèse Editeur : Bordeaux : Université de Bordeaux Année de publication : 2020 Importance : 195 p. Format : 21 x 30 cm Note générale : bibliographie Thèse présentée pour obtenir le grade de Docteur de l'Université de Bordeaux, Spécialité Informatique Langues : Français (fre) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage profond [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] classification par réseau neuronal récurrent [Termes IGN] classification semi-dirigée [Termes IGN] corpus [Termes IGN] échantillonnage de données [Termes IGN] processus de hiérarchisation analytique [Termes IGN] reconnaissance d'objets [Termes IGN] taille du jeu de données [Termes IGN] vision par ordinateur Index. décimale : THESE Thèses et HDR Résumé : (auteur) Deep convolutional neural networks (DCNN) have recently protagonized a revolution in large-scale object recognition. They have changed the usual computer vision practices of hand-engineered features, with their ability to hierarchically learn representative features from data with a pertinent classifier. Together with hardware advances, they have made it possible to effectively exploit the ever-growing amounts of image data gathered online. However, in specific domains like healthcare and industrial applications, data is much less abundant, and expert labeling costs higher than those of general purpose image datasets. This scarcity scenario leads to this thesis' core question: can these limited-data domains profit from the advantages of DCNNs for image classification? This question has been addressed throughout this work, based on an extensive study of literature, divided in two main parts, followed by proposal of original models and mechanisms.The first part reviews object recognition from an interdisciplinary double-viewpoint. First, it resorts to understanding the function of vision from a biological stance, comparing and contrasting to DCNN models in terms of structure, function and capabilities. Second, a state-of-the-art review is established aiming to identify the main architectural categories and innovations in modern day DCNNs. This interdisciplinary basis fosters the identification of potential mechanisms - inspired both from biological and artificial structures — that could improve image recognition under difficult situations. Recurrent processing is a clear example: while not completely absent from the "deep vision" literature, it has mostly been applied to videos — due to their inherently sequential nature. From biology however it is clear such processing plays a role in refining our perception of a still scene. This theme is further explored through a dedicated literature review focused on recurrent convolutional architectures used in image classification.The second part carries on in the spirit of improving DCNNs, this time focusing more specifically on our central question: deep learning over small datasets. First, the work proposes a more detailed and precise discussion of the small sample problem and its relation to learning hierarchical features with deep models. This discussion is followed up by a structured view of the field, organizing and discussing the different possible paths towards adapting deep models to limited data settings. Rather than a raw listing, this review work aims to make sense out of the myriad of approaches in the field, grouping methods with similar intent or mechanism of action, in order to guide the development of custom solutions for small-data applications. Second, this study is complemented by an experimental analysis, exploring small data learning with the proposition of original models and mechanisms (previously published as a journal paper).In conclusion, it is possible to apply deep learning to small datasets and obtain good results, if done in a thoughtful fashion. On the data path, one shall try gather more information from additional related data sources if available. On the complexity path, architecture and training methods can be calibrated in order to profit the most from any available domain-specific side-information. Proposals concerning both of these paths get discussed in detail throughout this document. Overall, while there are multiple ways of reducing the complexity of deep learning with small data samples, there is no universal solution. Each method has its own drawbacks and practical difficulties and needs to be tailored specifically to the target perceptual task at hand. Note de contenu : 1- Introduction I- Object recognition with deep convolutional neural networks 2- Convolutional neural networks and visual system modeling 3- Feedforward CNN architectures for object recognition 4- Recurrent and feedback CNN architectures for object recognition II- Image classification on small datasets 5- A review of strategies to use deep learning under limited data 6- Analysis of DCNN applied to small sample learning using data prototypes 7 Conclusion Numéro de notice : 28312 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Thèse française Note de thèse : thèse de Doctorat : Informatique : Bordeaux : 2020 Organisme de stage : Laboratoire bordelais de recherche en informatique DOI : sans En ligne : https://tel.archives-ouvertes.fr/tel-03129189v2/document Format de la ressource électronique : URL Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=98233