Diagnosing Ensemble Few-Shot Classifiers

Diagnosing Ensemble Few-Shot Classifiers

The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis metho...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on visualization and computer graphics. - 1996. - 28(2022), 9 vom: 14. Sept., Seite 3292-3306
Auteur principal: Yang, Weikai (Auteur)
Autres auteurs: Ye, Xi, Zhang, Xingxing, Xiao, Lanxi, Xia, Jiazhi, Wang, Zhongyuan, Zhu, Jun, Pfister, Hanspeter, Liu, Shixia
Format: Article en ligne
Langue:English
Publié: 2022
Accès à la collection:IEEE transactions on visualization and computer graphics
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM342180800
003 DE-627
005 20250303112242.0
007 cr uuu---uuuuu
008 231226s2022 xx |||||o 00| ||eng c
024 7 |a 10.1109/TVCG.2022.3182488  |2 doi 
028 5 2 |a pubmed25n1140.xml 
035 |a (DE-627)NLM342180800 
035 |a (NLM)35696465 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Yang, Weikai  |e verfasserin  |4 aut 
245 1 0 |a Diagnosing Ensemble Few-Shot Classifiers 
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 01.08.2022 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a The base learners and labeled samples (shots) in an ensemble few-shot classifier greatly affect the model performance. When the performance is not satisfactory, it is usually difficult to understand the underlying causes and make improvements. To tackle this issue, we propose a visual analysis method, FSLDiagnotor. Given a set of base learners and a collection of samples with a few shots, we consider two problems: 1) finding a subset of base learners that well predict the sample collections; and 2) replacing the low-quality shots with more representative ones to adequately represent the sample collections. We formulate both problems as sparse subset selection and develop two selection algorithms to recommend appropriate learners and shots, respectively. A matrix visualization and a scatterplot are combined to explain the recommended learners and shots in context and facilitate users in adjusting them. Based on the adjustment, the algorithm updates the recommendation results for another round of improvement. Two case studies are conducted to demonstrate that FSLDiagnotor helps build a few-shot classifier efficiently and increases the accuracy by 12% and 21%, respectively 
650 4 |a Journal Article 
700 1 |a Ye, Xi  |e verfasserin  |4 aut 
700 1 |a Zhang, Xingxing  |e verfasserin  |4 aut 
700 1 |a Xiao, Lanxi  |e verfasserin  |4 aut 
700 1 |a Xia, Jiazhi  |e verfasserin  |4 aut 
700 1 |a Wang, Zhongyuan  |e verfasserin  |4 aut 
700 1 |a Zhu, Jun  |e verfasserin  |4 aut 
700 1 |a Pfister, Hanspeter  |e verfasserin  |4 aut 
700 1 |a Liu, Shixia  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on visualization and computer graphics  |d 1996  |g 28(2022), 9 vom: 14. Sept., Seite 3292-3306  |w (DE-627)NLM098269445  |x 1941-0506  |7 nnas 
773 1 8 |g volume:28  |g year:2022  |g number:9  |g day:14  |g month:09  |g pages:3292-3306 
856 4 0 |u http://dx.doi.org/10.1109/TVCG.2022.3182488  |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 28  |j 2022  |e 9  |b 14  |c 09  |h 3292-3306