dc.contributor.author | Agarwal, Rohit | |
dc.contributor.author | Das, Gyanendra | |
dc.contributor.author | Aggarwal, Saksham | |
dc.contributor.author | Horsch, Ludwig Alexander | |
dc.contributor.author | Prasad, Dilip Kumar | |
dc.date.accessioned | 2024-03-19T14:36:29Z | |
dc.date.available | 2024-03-19T14:36:29Z | |
dc.date.issued | 2023-05-05 | |
dc.description.abstract | Image retrieval has garnered a growing interest in recent times. The current approaches are either supervised or self-supervised. These methods do not exploit the benefits of hybrid learning using both supervision and self-supervision. We present a novel Master Assistant Buddy Network (MAB-Net) for image retrieval which incorporates both the learning mechanisms. MABNet consists of master and assistant block, both learning independently through supervision and collectively via self-supervision. The master guides the assistant by providing its knowledge base as a reference for self-supervision and the assistant reports its knowledge back to the master by weight transfer. We perform extensive experiments on the public datasets with and without post-processing. | en_US |
dc.identifier.citation | Agarwal R, Das, Aggarwal, Horsch A, Prasad DK. Mabnet: Master Assistant Buddy Network With Hybrid Learning for Image Retrieval. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. 2023 | en_US |
dc.identifier.cristinID | FRIDAID 2185313 | |
dc.identifier.doi | 10.1109/ICASSP49357.2023.10094987 | |
dc.identifier.issn | 1520-6149 | |
dc.identifier.issn | 2379-190X | |
dc.identifier.uri | https://hdl.handle.net/10037/33195 | |
dc.language.iso | eng | en_US |
dc.publisher | IEEE | en_US |
dc.relation.journal | Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing | |
dc.rights.accessRights | openAccess | en_US |
dc.rights.holder | Copyright 2023 The Author(s) | en_US |
dc.title | Mabnet: Master Assistant Buddy Network With Hybrid Learning for Image Retrieval | en_US |
dc.type.version | acceptedVersion | en_US |
dc.type | Journal article | en_US |
dc.type | Tidsskriftartikkel | en_US |
dc.type | Peer reviewed | en_US |