Please use this identifier to cite or link to this item:
http://bura.brunel.ac.uk/handle/2438/24436
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Wang, W | - |
dc.contributor.author | Zhao, Z | - |
dc.contributor.author | Wang, P | - |
dc.contributor.author | Su, F | - |
dc.contributor.author | Meng, H | - |
dc.date.accessioned | 2022-04-12T08:44:57Z | - |
dc.date.available | 2022-04-12T08:44:57Z | - |
dc.date.issued | 2022-03-22 | - |
dc.identifier | ORCiD: Weiqiu Wang https://orcid.org/0000-0001-9341-0380 | - |
dc.identifier | ORCiD: Zhicheng Zhao https://orcid.org/0000-0001-6506-7298 | - |
dc.identifier | ORCiD: Fei Su https://orcid.org/0000-0003-4245-4687 | - |
dc.identifier | ORCiD: Hongying Meng https://orcid.org/0000-0002-8836-1382 | - |
dc.identifier.citation | Wang, W. et al. (2022) 'Attentive Feature Augmentation for Long-Tailed Visual Recognition', IEEE Transactions on Circuits and Systems for Video Technology, 32 (9), pp. 5803 - 5816. doi: 10.1109/tcsvt.2022.3161427. | en_US |
dc.identifier.issn | 1051-8215 | - |
dc.identifier.uri | https://bura.brunel.ac.uk/handle/2438/24436 | - |
dc.description.abstract | Deep neural networks have achieved great success on many visual recognition tasks. However, training data with a long-tailed distribution dramatically degenerates the performance of recognition models. In order to relieve this imbalance problem, an effective Long-Tailed Visual Recognition (LTVR) framework is proposed based on learned balance and robust features under long-tailed distribution circumstances. In this framework, a plug-and-play Attentive Feature Augmentation (AFA) module is designed to mine class-related and variation-related features of original samples via a novel hierarchical channel attention mechanism. Then, those features are aggregated to synthesize fake features to cope with the imbalance of the original dataset. Moreover, a Lay-Back Learning Schedule (LBLS) is developed to ensure a good initialization of feature embedding. Extensive experiments are conducted with a two-stage training method to verify the effectiveness of the proposed framework on both feature learning and classifier rebalancing in the long-tailed image recognition task. Experimental results show that, when trained with imbalanced datasets, the proposed framework achieves superior performance over the state-of-the-art methods. | - |
dc.description.sponsorship | 10.13039/501100001809-National Natural Science Foundation of China (Grant Number: 62076033 and U1931202). | en_US |
dc.format.extent | 5803 - 5816 | - |
dc.format.medium | Print-Electronic | - |
dc.language.iso | en_US | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers (IEEE) | en_US |
dc.rights | Copyright © 2022 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/ | - |
dc.rights.uri | https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/ | - |
dc.subject | image classification | en_US |
dc.subject | long-tailed distribution | en_US |
dc.subject | data augmentation | en_US |
dc.subject | data synthesizing | en_US |
dc.title | Attentive Feature Augmentation for Long-Tailed Visual Recognition | en_US |
dc.type | Article | en_US |
dc.identifier.doi | https://doi.org/10.1109/tcsvt.2022.3161427 | - |
dc.relation.isPartOf | IEEE Transactions on Circuits and Systems for Video Technology | - |
pubs.issue | 9 | - |
pubs.publication-status | Published | - |
pubs.volume | 32 | - |
dc.identifier.eissn | 1558-2205 | - |
dcterms.dateAccepted | 2022-03-17 | - |
dc.rights.holder | Institute of Electrical and Electronics Engineers (IEEE) | - |
Appears in Collections: | Dept of Electronic and Electrical Engineering Research Papers |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
FullText.pdf | Copyright © 2022 Institute of Electrical and Electronics Engineers (IEEE). Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. See: https://journals.ieeeauthorcenter.ieee.org/become-an-ieee-journal-author/publishing-ethics/guidelinesand-policies/post-publication-policies/ | 1.77 MB | Adobe PDF | View/Open |
Items in BURA are protected by copyright, with all rights reserved, unless otherwise indicated.