Semi-Supervised Learning for FGVC With Out-of-Category Data

Semi-Supervised Learning for FGVC With Out-of-Category Data

Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are called for. Semi-supervised learning (SSL) techniques, acquiring knowledge from unlabeled data, provide a considerable means...

Ausführliche Beschreibung

Bibliographische Detailangaben
Veröffentlicht in:IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 5 vom: 04. Apr., Seite 2658-2671
1. Verfasser: Du, Ruoyi (VerfasserIn)
Weitere Verfasser: Chang, Dongliang, Ma, Zhanyu, Liang, Kongming, Song, Yi-Zhe, Guo, Jun
Format: Online-Aufsatz
Sprache:English
Veröffentlicht: 2024
Zugriff auf das übergeordnete Werk:IEEE transactions on pattern analysis and machine intelligence
Schlagworte:Journal Article
LEADER 01000caa a22002652 4500
001 NLM362949905
003 DE-627
005 20240404234319.0
007 cr uuu---uuuuu
008 231226s2024 xx |||||o 00| ||eng c
024 7 |a 10.1109/TPAMI.2023.3322463  |2 doi 
028 5 2 |a pubmed24n1364.xml 
035 |a (DE-627)NLM362949905 
035 |a (NLM)37801380 
040 |a DE-627  |b ger  |c DE-627  |e rakwb 
041 |a eng 
100 1 |a Du, Ruoyi  |e verfasserin  |4 aut 
245 1 0 |a Semi-Supervised Learning for FGVC With Out-of-Category Data 
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 03.04.2024 
500 |a published: Print-Electronic 
500 |a Citation Status PubMed-not-MEDLINE 
520 |a Despite great strides made on fine-grained visual classification (FGVC), current methods are still heavily reliant on fully-supervised paradigms where ample expert labels are called for. Semi-supervised learning (SSL) techniques, acquiring knowledge from unlabeled data, provide a considerable means forward and have shown great promise for coarse-grained problems. However, exiting SSL paradigms mostly assume in-category (i.e., category-aligned) unlabeled data, which hinders their effectiveness when re-proposed on FGVC. In this paper, we put forward a novel design specifically aimed at making out-of-category data work for semi-supervised FGVC. We work off an important assumption that all fine-grained categories naturally follow a hierarchical structure (e.g., the phylogenetic tree of "Aves" that covers all bird species). It follows that, instead of operating on individual samples, we can instead predict sample relations within this tree structure as the optimization goal of SSL. Beyond this, we further introduced two strategies uniquely brought by these tree structures to achieve inter-sample consistency regularization and reliable pseudo-relation. Our experimental results reveal that (i) the proposed method yields good robustness against out-of-category data, and (ii) it can be equipped with prior arts, boosting their performance thus yielding state-of-the-art results 
650 4 |a Journal Article 
700 1 |a Chang, Dongliang  |e verfasserin  |4 aut 
700 1 |a Ma, Zhanyu  |e verfasserin  |4 aut 
700 1 |a Liang, Kongming  |e verfasserin  |4 aut 
700 1 |a Song, Yi-Zhe  |e verfasserin  |4 aut 
700 1 |a Guo, Jun  |e verfasserin  |4 aut 
773 0 8 |i Enthalten in  |t IEEE transactions on pattern analysis and machine intelligence  |d 1979  |g 46(2024), 5 vom: 04. Apr., Seite 2658-2671  |w (DE-627)NLM098212257  |x 1939-3539  |7 nnns 
773 1 8 |g volume:46  |g year:2024  |g number:5  |g day:04  |g month:04  |g pages:2658-2671 
856 4 0 |u http://dx.doi.org/10.1109/TPAMI.2023.3322463  |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 46  |j 2024  |e 5  |b 04  |c 04  |h 2658-2671