Delving Into Generalizable Label Distribution Learning

Owing to the excellent capability in dealing with label ambiguity, Label Distribution Learning (LDL), as an emerging machine learning paradigm, has received extensive research in recent years. Though remarkable progress has been achieved in various tasks, one limitation with existing LDL methods is...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 10 vom: 03. Sept., Seite 8708-8724
1. Verfasser: Zhao, Xingyu (VerfasserIn)
Weitere Verfasser: Qi, Lei, An, Yuexuan, Geng, Xin
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2025
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM392370948
003 DE-627
005 20250918232109.0
007 cr uuu---uuuuu
008 250912s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3581552  |2 doi 
028 5 2 |a pubmed25n1573.xml 
035 |a (DE-627)NLM392370948 
035 |a (NLM)40536835 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Zhao, Xingyu  |e verfasserin  |4 aut 
245 1 0 |a Delving Into Generalizable Label Distribution Learning 
264 1 |c 2025 
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 18.09.2025 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Owing to the excellent capability in dealing with label ambiguity, Label Distribution Learning (LDL), as an emerging machine learning paradigm, has received extensive research in recent years. Though remarkable progress has been achieved in various tasks, one limitation with existing LDL methods is that they are all based on the i.i.d. assumption that training and test data are identically and independently distributed. As a result, they suffer obvious performance degradation and are no longer applicable when tested in out-of-distribution scenarios, which severely limits the application of LDL in many tasks. In this paper, we identify and investigate the Generalizable Label Distribution Learning (GLDL) problem. To handle such a challenging problem, we delve into the characteristics of GLDL and find that the label annotations changing with the variability of the domains is the underlying reason for the performance degradation of the existing methods. Inspired by this observation, we explore domain-invariant feature-label correlation information to reduce the impact of label annotations changing with domains and propose two practical methods. Extensive experiments verify the superior performance of the proposed methods. Our work fills the gap in benchmarks and techniques for practical GLDL problems 
650 4 |a Journal Article 
700 1 |a Qi, Lei  |e verfasserin  |4 aut 
700 1 |a An, Yuexuan  |e verfasserin  |4 aut 
700 1 |a Geng, Xin  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 47(2025), 10 vom: 03. Sept., Seite 8708-8724  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:47  |g year:2025  |g number:10  |g day:03  |g month:09  |g pages:8708-8724 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3581552  |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 47  |j 2025  |e 10  |b 03  |c 09  |h 8708-8724