Please use this identifier to cite or link to this item:
http://hdl.handle.net/10397/105550
DC Field | Value | Language |
---|---|---|
dc.contributor | Department of Computing | - |
dc.creator | Lin, D | - |
dc.creator | Wang, Y | - |
dc.creator | Liang, L | - |
dc.creator | Li, P | - |
dc.creator | Chen, CLP | - |
dc.date.accessioned | 2024-04-15T07:34:59Z | - |
dc.date.available | 2024-04-15T07:34:59Z | - |
dc.identifier.issn | 2162-237X | - |
dc.identifier.uri | http://hdl.handle.net/10397/105550 | - |
dc.language.iso | en | en_US |
dc.publisher | Institute of Electrical and Electronics Engineers | en_US |
dc.rights | ©2020 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. | en_US |
dc.rights | The following publication D. Lin, Y. Wang, L. Liang, P. Li and C. L. P. Chen, "Deep LSAC for Fine-Grained Recognition," in IEEE Transactions on Neural Networks and Learning Systems, vol. 33, no. 1, pp. 200-214, Jan. 2022 is available at https://doi.org/10.1109/TNNLS.2020.3027603. | en_US |
dc.subject | Convolutional neural network (CNN) | en_US |
dc.subject | Fine-grained recognition | en_US |
dc.subject | Object detection | en_US |
dc.subject | Pose alignment | en_US |
dc.subject | Semantic segmentation | en_US |
dc.title | Deep LSAC for fine-grained recognition | en_US |
dc.type | Journal/Magazine Article | en_US |
dc.identifier.spage | 200 | - |
dc.identifier.epage | 214 | - |
dc.identifier.volume | 33 | - |
dc.identifier.issue | 1 | - |
dc.identifier.doi | 10.1109/TNNLS.2020.3027603 | - |
dcterms.abstract | Fine-grained recognition emphasizes the identification of subtle differences among object categories given objects that appear in different shapes and poses. These variances should be reduced for reliable recognition. We propose a fine-grained recognition system that incorporates localization, segmentation, alignment, and classification in a unified deep neural network. The input to the classification module includes functions that enable backward-propagation (BP) in constructing the solver. Our major contribution is to propose a valve linkage function (VLF) for BP chaining and form our deep localization, segmentation, alignment, and classification (LSAC) system. The VLF can adaptively compromise errors of classification and alignment when training the LSAC model. It in turn helps to update the localization and segmentation. We evaluate our framework on two widely used fine-grained object data sets. The performance confirms the effectiveness of our LSAC system. | - |
dcterms.accessRights | open access | en_US |
dcterms.bibliographicCitation | IEEE transactions on neural networks and learning systems, Jan. 2022, v. 33, no. 1, p. 200-214 | - |
dcterms.isPartOf | IEEE transactions on neural networks and learning systems | - |
dcterms.issued | 2022-01 | - |
dc.identifier.scopus | 2-s2.0-85092927977 | - |
dc.identifier.pmid | 33048766 | - |
dc.identifier.eissn | 2162-2388 | - |
dc.description.validate | 202402 bcch | - |
dc.description.oa | Accepted Manuscript | en_US |
dc.identifier.FolderNumber | COMP-0432 | en_US |
dc.description.fundingSource | Others | en_US |
dc.description.fundingText | National Natural Science Foundation of China; Natural Science Foundation of Guangdong Province; Fundamental Research Funds for the Central Universities; National Key Research and Development Program of China; The Hong Kong Polytechnic University | en_US |
dc.description.pubStatus | Published | en_US |
dc.identifier.OPUS | 43000964 | en_US |
dc.description.oaCategory | Green (AAM) | en_US |
Appears in Collections: | Journal/Magazine Article |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Li_Deep_Lsac_Fine-Grained.pdf | Pre-Published version | 78.47 MB | Adobe PDF | View/Open |
Page views
15
Citations as of Jul 7, 2024
Downloads
3
Citations as of Jul 7, 2024
SCOPUSTM
Citations
7
Citations as of Jul 4, 2024
WEB OF SCIENCETM
Citations
7
Citations as of Jul 4, 2024
Google ScholarTM
Check
Altmetric
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.