Learning Calibrated Class Centers for Few-Shot Classification by Pair-Wise Similarity

Learning Calibrated Class Centers for Few-Shot Classification by Pair-Wise Similarity

Metric-based methods achieve promising performance on few-shot classification by learning clusters on support samples and generating shared decision boundaries for query samples. However, existing methods ignore the inaccurate class center approximation introduced by the limited number of support sa...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society. - 1992. - 31(2022) vom: 21., Seite 4543-4555
1. Verfasser: Guo, Yurong (VerfasserIn)
Weitere Verfasser: Du, Ruoyi, Li, Xiaoxu, Xie, Jiyang, Ma, Zhanyu, Dong, Yuan
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2022
Zugriff auf das übergeordnete Werk:IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
Schlagworte:Journal Article
LEADER 01000naa a22002652 4500
001 NLM34288350X
003 DE-627
005 20231226015134.0
007 cr uuu---uuuuu
008 231226s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TIP.2022.3184813  |2 doi 
028 5 2 |a pubmed24n1142.xml 
035 |a (DE-627)NLM34288350X 
035 |a (NLM)35767479 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Guo, Yurong  |e verfasserin  |4 aut 
245 1 0 |a Learning Calibrated Class Centers for Few-Shot Classification by Pair-Wise Similarity 
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 06.07.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Metric-based methods achieve promising performance on few-shot classification by learning clusters on support samples and generating shared decision boundaries for query samples. However, existing methods ignore the inaccurate class center approximation introduced by the limited number of support samples, which consequently leads to biased inference. Therefore, in this paper, we propose to reduce the approximation error by class center calibration. Specifically, we introduce the so-called Pair-wise Similarity Module (PSM) to generate calibrated class centers adapted to the query sample by capturing the semantic correlations between the support and the query samples, as well as enhancing the discriminative regions on support representation. It is worth noting that the proposed PSM is a simple plug-and-play module and can be inserted into most metric-based few-shot learning models. Through extensive experiments in metric-based models, we demonstrate that the module significantly improves the performance of conventional few-shot classification methods on four few-shot image classification benchmark datasets. Codes are available at: https://github.com/PRIS-CV/Pair-wise-Similarity-module 
650 4 |a Journal Article 
700 1 |a Du, Ruoyi  |e verfasserin  |4 aut 
700 1 |a Li, Xiaoxu  |e verfasserin  |4 aut 
700 1 |a Xie, Jiyang  |e verfasserin  |4 aut 
700 1 |a Ma, Zhanyu  |e verfasserin  |4 aut 
700 1 |a Dong, Yuan  |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 31(2022) vom: 21., Seite 4543-4555  |w (DE-627)NLM09821456X  |x 1941-0042  |7 nnns 
773 1 8 |g volume:31  |g year:2022  |g day:21  |g pages:4543-4555 
856 4 0 |u http://dx.doi.org/10.1109/TIP.2022.3184813  |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 31  |j 2022  |b 21  |h 4543-4555