|
|
|
|
| LEADER |
01000caa a22002652 4500 |
| 001 |
NLM373580738 |
| 003 |
DE-627 |
| 005 |
20240626232553.0 |
| 007 |
cr uuu---uuuuu |
| 008 |
240614s2024 xx |||||o 00| ||eng c |
| 024 |
7 |
|
|a 10.1109/TIP.2024.3411474
|2 doi
|
| 028 |
5 |
2 |
|a pubmed24n1452.xml
|
| 035 |
|
|
|a (DE-627)NLM373580738
|
| 035 |
|
|
|a (NLM)38870000
|
| 040 |
|
|
|a DE-627
|b ger
|c DE-627
|e rakwb
|
| 041 |
|
|
|a eng
|
| 100 |
1 |
|
|a Zhao, Li-Jun
|e verfasserin
|4 aut
|
| 245 |
1 |
0 |
|a Angular Isotonic Loss Guided Multi-Layer Integration for Few-Shot Fine-Grained Image Classification
|
| 264 |
|
1 |
|c 2024
|
| 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 25.06.2024
|
| 500 |
|
|
|a published: Print-Electronic
|
| 500 |
|
|
|a Citation Status PubMed-not-MEDLINE
|
| 520 |
|
|
|a Recent research on few-shot fine-grained image classification (FSFG) has predominantly focused on extracting discriminative features. The limited attention paid to the role of loss functions has resulted in weaker preservation of similarity relationships between query and support instances, thereby potentially limiting the performance of FSFG. In this regard, we analyze the limitations of widely adopted cross-entropy loss and introduce a novel Angular ISotonic (AIS) loss. The AIS loss introduces an angular margin to constrain the prototypes to maintain a certain distance from a pre-set threshold. It guides the model to converge more stably, learn clearer boundaries among highly similar classes, and achieve higher accuracy faster with limited instances. Moreover, to better accommodate the feature requirements of the AIS loss and fully exploit its potential in FSFG, we propose a Multi-Layer Integration (MLI) network that captures object features from multiple perspectives to provide more comprehensive and informative representations of the input images. Extensive experiments demonstrate the effectiveness of our proposed method on four standard fine-grained benchmarks. Codes are available at: https://github.com/Legenddddd/AIS-MLI
|
| 650 |
|
4 |
|a Journal Article
|
| 700 |
1 |
|
|a Chen, Zhen-Duo
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Ma, Zhen-Xiang
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Luo, Xin
|e verfasserin
|4 aut
|
| 700 |
1 |
|
|a Xu, Xin-Shun
|e verfasserin
|4 aut
|
| 773 |
0 |
8 |
|i Enthalten in
|t IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
|d 1992
|g 33(2024) vom: 13., Seite 3778-3792
|w (DE-627)NLM09821456X
|x 1941-0042
|7 nnns
|
| 773 |
1 |
8 |
|g volume:33
|g year:2024
|g day:13
|g pages:3778-3792
|
| 856 |
4 |
0 |
|u http://dx.doi.org/10.1109/TIP.2024.3411474
|3 Volltext
|
| 912 |
|
|
|a GBV_USEFLAG_A
|
| 912 |
|
|
|a SYSFLAG_A
|
| 912 |
|
|
|a GBV_NLM
|
| 912 |
|
|
|a GBV_ILN_350
|
| 951 |
|
|
|a AR
|
| 952 |
|
|
|d 33
|j 2024
|b 13
|h 3778-3792
|