Collaborative Learning in Computer Vision

The science of designing machines to extract meaningful information from digital images, videos, and other visual inputs is known as Computer Vision (CV). Deep learning algorithms cope CV problems by automatically learning task-specific features. Especially, Deep Neural Networks (DNNs) have become an essential component in CV solutions due to their ability to encode large amounts of data and capacity to manipulate billions of model parameters. Unlike machines, humans learn by rapidly constructing abstract models. This is undoubtedly due to the fact that good teachers supply their students with much more than just the correct answer; they also provide intuitive comments, comparisons, and explanations. In deep learning, the availability of such auxiliary information at training time (but not at test time) is referred to as learning by Privileged Information (PI). Typically, predictions (e.g., soft labels) produced by a bigger and better network teacher are used as structured knowledge to supervise the training of a smaller network student, helping the student network to generalize better than that trained from scratch. This dissertation focuses on the category of deep learning systems known as Collaborative Learning, where one DNN model helps other models or several models help each other during training to achieve strong generalization and thus high performance. The question we address here is thus the following: how can we take advantage of PI for training a deep learning model, knowing that, at test time, such PI might be missing? In this context, we introduce new methods to tackle several challenging real-world computer vision problems. First, we propose a method for model compression that leverages PI in a teacher-student framework along with customizable block-wise optimization for learning a target-specific lightweight structure of the neural network. In particular, the proposed resource-aware optimization is employed on suitable parts of the student network while respecting the expected resource budget ...

Università degli studi di Genova

2022-02-25

info:eu-repo/semantics/doctoralThesis ; [Doctoral and postdoctoral thesis]

eng

Settore INF/01 - Informatica

004 Data processing & computer science (computed)

info:eu-repo/semantics/openAccess

http://hdl.handle.net/11567/1069010
https://doi.org/10.15167/ahmed-waqar_phd2022-02-25

Università degli Studi di Genova: CINECA IRIS  

• URL: https://iris.unige.it/
• Research Organization Registry (ROR): University of Genoa
• Continent: Europe
• Country: it
• Number of documents: 176,907
• Open Access: 13,627 (8%)
• Type: Academic publications
• System: DSpace IRIS
• Content provider indexed in BASE since: 2016-04-27
• BASE URL: https://www.base-search.net/Search/Results?q=coll:ftunivgenova