Sun, N. and Yang, P. orcid.org/0000-0002-8553-7127 (2023) T2L: Trans-transfer Learning for few-shot fine-grained visual categorization with extended adaptation. Knowledge-Based Systems, 264. 110329. ISSN 0950-7051
Abstract
Fine-grained visual categorization requires the ability to distinguish categories with subtle differences, which is also a problem constantly burdened by collecting and labelling massive volume of samples. While transfer learning is extensively used in fine-grained visual categorization, these approaches generally does not work under few-shot regime. As apposed to meta-learning which suffers limitations such as shallow adaptation, and traditional transfer learning which is not task-oriented, we propose a novel transfer learning approach which we refer to as Trans-transfer Learning (T2L). Firstly, a two-phase learning framework is proposed to facilitate task orientation and deep adaptation. Secondly, a novel explainable-learning based procedure is integrated into the second phase to reconfigure the network for training on few samples, after which a deep adaptation procedure is conducted by simultaneously optimizing the feature extractor and the classification boundaries. It is motivated by the fact that a large factor of the over-fitting under few-shot regime, comes from noises that appear in every layers of the activation. The reconfigured model can train solely based on inter-class differences, which not only alleviates over-fitting, but also rediscovers more discriminating features. The proposed approach is comparatively evaluated with state-of-the-art approaches in this field and demonstrates better performances consistently.
Metadata
Item Type: | Article |
---|---|
Authors/Creators: |
|
Copyright, Publisher and Additional Information: | © 2023 Published by Elsevier B.V. This is an author produced version of a paper subsequently published in Knowledge-Based Systems. Uploaded in accordance with the publisher's self-archiving policy. Article available under the terms of the CC-BY-NC-ND licence (https://creativecommons.org/licenses/by-nc-nd/4.0/). |
Keywords: | Computer vision; Fine-grained visual categorization; Few-shot learning; Transfer learning |
Dates: |
|
Institution: | The University of Sheffield |
Academic Units: | The University of Sheffield > Faculty of Engineering (Sheffield) > Department of Computer Science (Sheffield) |
Depositing User: | Symplectic Sheffield |
Date Deposited: | 30 Jan 2023 17:07 |
Last Modified: | 27 Sep 2024 10:26 |
Status: | Published |
Publisher: | Elsevier |
Refereed: | Yes |
Identification Number: | 10.1016/j.knosys.2023.110329 |
Open Archives Initiative ID (OAI ID): | oai:eprints.whiterose.ac.uk:195751 |