Deep LSAC for Fine-Grained Recognition
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.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2022 |
---|---|
Erschienen: |
2022 |
Enthalten in: |
Zur Gesamtaufnahme - volume:33 |
---|---|
Enthalten in: |
IEEE transactions on neural networks and learning systems - 33(2022), 1 vom: 13. Jan., Seite 200-214 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Lin, Di [VerfasserIn] |
---|
Links: |
---|
Themen: |
---|
Anmerkungen: |
Date Revised 06.01.2022 published: Print-Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.1109/TNNLS.2020.3027603 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM316184489 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM316184489 | ||
003 | DE-627 | ||
005 | 20231225160531.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2022 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1109/TNNLS.2020.3027603 |2 doi | |
028 | 5 | 2 | |a pubmed24n1053.xml |
035 | |a (DE-627)NLM316184489 | ||
035 | |a (NLM)33048766 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Lin, Di |e verfasserin |4 aut | |
245 | 1 | 0 | |a Deep LSAC for Fine-Grained Recognition |
264 | 1 | |c 2022 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Revised 06.01.2022 | ||
500 | |a published: Print-Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a 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 | ||
650 | 4 | |a Journal Article | |
700 | 1 | |a Wang, Yi |e verfasserin |4 aut | |
700 | 1 | |a Liang, Lingyu |e verfasserin |4 aut | |
700 | 1 | |a Li, Ping |e verfasserin |4 aut | |
700 | 1 | |a Chen, C L Philip |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t IEEE transactions on neural networks and learning systems |d 2012 |g 33(2022), 1 vom: 13. Jan., Seite 200-214 |w (DE-627)NLM23236897X |x 2162-2388 |7 nnns |
773 | 1 | 8 | |g volume:33 |g year:2022 |g number:1 |g day:13 |g month:01 |g pages:200-214 |
856 | 4 | 0 | |u http://dx.doi.org/10.1109/TNNLS.2020.3027603 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 33 |j 2022 |e 1 |b 13 |c 01 |h 200-214 |