ClusMatch : Improving Deep Clustering by Unified Positive and Negative Pseudo-Label Learning

Recently, deep clustering methods have achieved remarkable results compared to traditional clustering approaches. However, its performance remains constrained by the absence of annotations. A thought-provoking observation is that there is still a significant gap between deep clustering and semi-supe...

Description complète

Détails bibliographiques
Publié dans:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 11 vom: 06. Okt., Seite 9688-9701
Auteur principal: Wu, Jianlong (Auteur)
Autres auteurs: Li, Zihan, Sun, Wei, Yin, Jianhua, Nie, Liqiang, Lin, Zhouchen
Format: Article en ligne
Langue:English
Publié: 2025
Accès à la collection:IEEE transactions on pattern analysis and machine intelligence
Sujets:Journal Article
LEADER 01000caa a22002652c 4500
001 NLM389469106
003 DE-627
005 20251007231847.0
007 cr uuu---uuuuu
008 250716s2025 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2025.3588239  |2 doi 
028 5 2 |a pubmed25n1591.xml 
035 |a (DE-627)NLM389469106 
035 |a (NLM)40663672 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Wu, Jianlong  |e verfasserin  |4 aut 
245 1 0 |a ClusMatch  |b Improving Deep Clustering by Unified Positive and Negative Pseudo-Label 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 06.10.2025 
500 |a published: Print 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Recently, deep clustering methods have achieved remarkable results compared to traditional clustering approaches. However, its performance remains constrained by the absence of annotations. A thought-provoking observation is that there is still a significant gap between deep clustering and semi-supervised classification methods. Even with only a few labeled samples, the accuracy of semi-supervised learning is much higher than that of clustering. Given that we can annotate a small number of samples in a certain unsupervised way, the clustering task can be naturally transformed into a semi-supervised setting, thereby achieving comparable performance. Based on this intuition, we propose ClusMatch, a unified positive and negative pseudo-label learning based semi-supervised learning framework, which is pluggable and can be applied to existing deep clustering methods. Specifically, we first leverage the pre-trained deep clustering network to compute predictions for all samples, and then design specialized selection strategies to pick out a few high-quality samples as labeled samples for supervised learning. For the unselected samples, the novel unified positive and negative pseudo-label learning is introduced to provide additional supervised signals for semi-supervised fine-tuning. We also propose an adaptive positive-negative threshold learning strategy to further enhance the confidence of generated pseudo-labels. Extensive experiments on six widely-used datasets and one large-scale dataset demonstrate the superiority of our proposed ClusMatch. For example, ClusMatch achieves a significant accuracy improvement of 5.4% over the state-of-the-art method ProPos on an average of these six datasets 
650 4 |a Journal Article 
700 1 |a Li, Zihan  |e verfasserin  |4 aut 
700 1 |a Sun, Wei  |e verfasserin  |4 aut 
700 1 |a Yin, Jianhua  |e verfasserin  |4 aut 
700 1 |a Nie, Liqiang  |e verfasserin  |4 aut 
700 1 |a Lin, Zhouchen  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 47(2025), 11 vom: 06. Okt., Seite 9688-9701  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnas 
773 1 8 |g volume:47  |g year:2025  |g number:11  |g day:06  |g month:10  |g pages:9688-9701 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2025.3588239  |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 11  |b 06  |c 10  |h 9688-9701