Learning optimal inter-class margin adaptively for few-shot class-incremental learning via neural collapse-based meta-learning

↓ Direkt till sidans innehåll
↓ Direkt till sidans sekundära innehåll (sidomenyn)

Sökning: onr:"swepub:oai:DiVA.org:hh-52738" > Learning optimal in...

1 av 1
Föregående post
Nästa post
Till träfflistan

Ran, HangChinese Academy Of Sciences, Beijing, China; University Of Chinese Academy Of Sciences, Beijing, China (författare)

Learning optimal inter-class margin adaptively for few-shot class-incremental learning via neural collapse-based meta-learning

Artikel/kapitelEngelska2024

Förlag, utgivningsår, omfång ...

London :Elsevier,2024
printrdacarrier

Nummerbeteckningar

LIBRIS-ID:oai:DiVA.org:hh-52738
https://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-52738URI
https://doi.org/10.1016/j.ipm.2024.103664DOI

Kompletterande språkuppgifter

Språk:engelska
Sammanfattning på:engelska

Ingår i deldatabas

SwePubSwePub

Klassifikation

Ämneskategori:ref swepub-contenttype
Ämneskategori:art swepub-publicationtype

Anmärkningar

his work is supported by the National Natural Science Foundation of China (No. 62373343); and the Beijing Natural Science Foundation, China (No. L233036).
Few-Shot Class-Incremental Learning (FSCIL) aims to learn new classes incrementally with a limited number of samples per class. It faces issues of forgetting previously learned classes and overfitting on few-shot classes. An efficient strategy is to learn features that are discriminative in both base and incremental sessions. Current methods improve discriminability by manually designing inter-class margins based on empirical observations, which can be suboptimal. The emerging Neural Collapse (NC) theory provides a theoretically optimal inter-class margin for classification, serving as a basis for adaptively computing the margin. Yet, it is designed for closed, balanced data, not for sequential or few-shot imbalanced data. To address this gap, we propose a Meta-learning- and NC-based FSCIL method, MetaNC-FSCIL, to compute the optimal margin adaptively and maintain it at each incremental session. Specifically, we first compute the theoretically optimal margin based on the NC theory. Then we introduce a novel loss function to ensure that the loss value is minimized precisely when the inter-class margin reaches its theoretically best. Motivated by the intuition that “learn how to preserve the margin” matches the meta-learning's goal of “learn how to learn”, we embed the loss function in base-session meta-training to preserve the margin for future meta-testing sessions. Experimental results demonstrate the effectiveness of MetaNC-FSCIL, achieving superior performance on multiple datasets. The code is available at https://github.com/qihangran/metaNC-FSCIL. © 2024 The Author(s)

Ämnesord och genrebeteckningar

NATURVETENSKAP Data- och informationsvetenskap hsv//swe
NATURAL SCIENCES Computer and Information Sciences hsv//eng
Few-shot class-incremental learning
Meta-learning
Neural collapse

Biuppslag (personer, institutioner, konferenser, titlar ...)

Li, WeijunChinese Academy Of Sciences, Beijing, China; University Of Chinese Academy Of Sciences, Beijing, China (författare)
Li, LusiOld Dominion University, Norfolk, United States (författare)
Tian, SongsongChinese Academy Of Sciences, Beijing, China; University Of Chinese Academy Of Sciences, Beijing, China (författare)
Ning, XinChinese Academy Of Sciences, Beijing, China; University Of Chinese Academy Of Sciences, Beijing, China; Cognitive Computing Technology Joint Laboratory, Beijing, China (författare)
Tiwari, Prayag,1991-Högskolan i Halmstad,Akademin för informationsteknologi(Swepub:hh)pratiw (författare)
Chinese Academy Of Sciences, Beijing, China; University Of Chinese Academy Of Sciences, Beijing, ChinaOld Dominion University, Norfolk, United States (creator_code:org_t)

Sammanhörande titlar

Ingår i:Information Processing & ManagementLondon : Elsevier61:30306-45731873-5371

Internetlänk

Hitta via bibliotek

Information Processing & Management (Sök värdpublikationen i LIBRIS)

Till lärosätets databas

1 av 1
Föregående post
Nästa post
Till träfflistan

Hitta mer i SwePub

Av författaren/redakt...: Ran, Hang; Li, Weijun; Li, Lusi; Tian, Songsong; Ning, Xin; Tiwari, Prayag, ...

Om ämnet

NATURVETENSKAP: NATURVETENSKAP; och Data och informa ...

Artiklar i publikationen: Information Proc ...

Av lärosätet: Högskolan i Halmstad

Sök utanför SwePub

Sök vidare i:: Google; Google Book Search; Google Scholar

Kungliga biblioteket hanterar dina personuppgifter i enlighet med EU:s dataskyddsförordning (2018), GDPR. Läs mer om hur det funkar här.
Så här hanterar KB dina uppgifter vid användning av denna tjänst.

LIBRIS.kb.se