Aristotle University Of Thessaloniki (AUTH)
Deep learning techniques in digital media
Abstract
dc:descriptionRecent advances in deep learning (DL) provided significant performance increase on various digital media analysis tasks, such as image classification and retrieval. However, despite their effectiveness, DL models suffer from high complexity. This constitutes a major impediment on applying these models on devices with restricted computational power. In this Ph.D thesis, we deal with three different digital media analysis problems, that is content based image retrieval, image classification, and video captioning, utilizing DL techniques. The principal goals of this thesis can be summarized in developing deep representation learning methods oriented to the specific digital media analysis tasks, and in developing lightweight DL methods that allow for deploying them on devices with restricted computational power. To this end, firstly a deep representation learning method for producing efficient retrieval oriented representations was proposed. Subsequently, the proposed method was properly adapted in order to learn more efficient representations considering both the retrieval performance, and the memory requirements and the retrieval speed. Next, lightweight DL models capable of operating even in real-time for high resolution input, on devices with limited computation power were proposed, for addressing generic problems of image classification. In addition, various regularization techniques based on the concept of multitask learning were proposed (e.g., graph embedding based regularization, regularization based on the criterion of quadratic mutual information), improving the generalization ability of the proposed lightweight models. Furthermore, two online self distillation methods were proposed, allowing for training efficient lightweight models in generic classification problems. Finally, a video captioning method was proposed. The proposed method was capable of capturing different kinds of information, producing improved performance in the video captioning task.
Degree
thesis:*- Grantor dc:publisher
- Aristotle University Of Thessaloniki (AUTH)
- Year dc:date
- 2021
Author and committee
dc:creator, dc:contributor.*- Authors dc:creator
-
- Tzelepi, Maria
- Τζελέπη, Μαρία
Subjects
dc:subject × 14- Βαθιά μάθηση
- Βαθιά μάθηση για ανάκτηση εικόνων με βάση το σημασιολογικό τους περιεχόμενο
- Τεχνικές κανονικοποίησης σε ελαφρά μοντέλα βαθιάς μάθησης
- Βαθιά απόσταξη γνώσης
- Deep learning
- Deep learning for content based image retrieval
- Regularization techniques in lightweight deep learning models
- Deep knowledge distillation
- Επιστήμη Ηλεκτρονικών Υπολογιστών και Πληροφορική
- Φυσικές Επιστήμες
- Τεχνητή νοημοσύνη
- Computer and Information Sciences
- Natural Sciences
- Artificial Intelligence
Rights
- Language dc:language
- eng
Identifiers
dc:identifier.*- Identifier
- 10.12681/eadd/49149