Παρακαλώ χρησιμοποιήστε αυτό το αναγνωριστικό για να παραπέμψετε ή να δημιουργήσετε σύνδεσμο προς αυτό το τεκμήριο:
https://hdl.handle.net/123456789/1119| Τύπος: | Πρακτικά συνεδρίου |
| Τίτλος: | Semantic information in gating patterns of dynamic Convolutional Neural Networks |
| Συγγραφέας: | [EL] Θεοδωρακόπουλος, Ηλίας[EN] Theodorakopoulos, Ilias [EL] Οικονόμου, Γεώργιος[EN] Economou, George |
| Ημερομηνία: | 12/07/2021 |
| Περίληψη: | Dynamic Convolutional Neural Networks are an emerging class of models characterized by their ability to dynamically adjust inference complexity at run-time, by identifying parts of the model with minimal contribution to the result and skipping the corresponding computations. A prominent such category includes models that generate binary gating signals indicating whether specific convolutional kernels need to be computed or can be omitted based on the characteristics of each processed datum. These signals are usually generated by branches of the same model which are typically learned simultaneously to the main task, with their main objective being to enable good performance with parsimony of computations. We argue that such objective incentivizes the model to implicitly optimize and utilize kernels in class/concept –specific groups, hence ascribing semantic information to the gating signals. We demonstrate this behavior by studying the characteristics of such signals for popular CNN architectures in the ImageNet database. By comparing the relationship between gating signals from different visual categories in the ImageNet hierarchy, it is shown that the gating patterns’ dissimilarity correlates well with semantic span of the underlying classes. It is also demonstrated that through appropriate distance measures, gating patterns can be used for ranking classes’ similarity with comparable performance to that off standard CNN-generated image descriptors, but in a significantly more compact representation due to their binary nature. |
| Γλώσσα: | Αγγλικά |
| Τόπος δημοσίευσης: | Chania Crete, Greece |
| Σελίδες: | 8 |
| DOI: | 10.1109/IISA52424.2021.9555567 |
| ISBN: | 978-1-6654-0032-9 |
| Θεματική κατηγορία: | [EL] Επιστήμη ηλεκτρονικών υπολογιστών και Πληροφορική, άλλοι τομείς[EN] Computer and Information sciences, miscellaneous |
| Λέξεις-κλειδιά: | Dynamic Convolutional Neural Networks; Semantic Similarity; Class Ranking; Gating Networks; Tverksy Similarity; ImageNet Hierarchy |
| Κάτοχος πνευματικών δικαιωμάτων: | ©2021 IEEE |
| Ηλεκτρονική διεύθυνση του τεκμηρίου στον εκδότη: | https://ieeexplore.ieee.org/abstract/document/9555567 |
| Ηλεκτρονική διεύθυνση περιοδικού: | https://ieeexplore.ieee.org/xpl/conhome/9555494/proceeding |
| Τίτλος πηγής δημοσίευσης: | 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) Proceedings |
| Όνομα εκδήλωσης: | 2021 12th International Conference on Information, Intelligence, Systems & Applications (IISA) |
| Τοποθεσία εκδήλωσης: | Chania Crete, Greece |
| Ημ/νία έναρξης εκδήλωσης: | 12/07/2021 |
| Ημ/νία λήξης εκδήλωσης: | 14/07/2021 |
| Σημειώσεις: | This research is co-financed by Greece and the European Union (European Social Fund- ESF) through the Operational Programme «Human Resources Development, Education and Lifelong Learning» in the context of the project “Reinforcement of Postdoctoral Researchers - 2nd Cycle” (MIS-5033021), implemented by the State Scholarships Foundation (ΙΚΥ). |
| Εμφανίζεται στις συλλογές: | Μεταδιδακτορικοί ερευνητές |
Αρχεία σε αυτό το τεκμήριο:
Το πλήρες κείμενο αυτού του τεκμηρίου δεν διατίθεται προς το παρόν από το αποθετήριο