FeTT: Class-Incremental Learning with Feature Transformation Tuning

Sunyuan Qiang and Yanyan Liang ()
Additional contact information
Sunyuan Qiang: Faculty of Innovation Engineering, Macau University of Science and Technology, Macau SAR 999078, China
Yanyan Liang: Faculty of Innovation Engineering, Macau University of Science and Technology, Macau SAR 999078, China

Mathematics, 2025, vol. 13, issue 7, 1-19

Abstract: Class-incremental learning (CIL) enables models to continuously acquire knowledge and adapt in an ever-changing environment. However, one primary challenge lies in the trade-off between the stability and plasticity, i.e., plastically expand the novel knowledge base and stably retaining previous knowledge without catastrophic forgetting. We find that even recent promising CIL methods via pre-trained models (PTMs) still suffer from this dilemma. To this end, this paper begins by analyzing the aforementioned dilemma from the perspective of marginal distribution for data categories. Then, we propose the feature transformation tuning (FeTT) model, which concurrently alleviates the inadequacy of previous PTM-based CIL in terms of stability and plasticity. Specifically, we apply the parameter-efficient fine-tuning (PEFT) strategies solely in the first CIL task to bridge the domain gap between the PTMs and downstream task dataset. Subsequently, the model is kept fixed to maintain stability and avoid discrepancies in training data distributions. Moreover, feature transformation is employed to regulate the backbone representations, boosting the model’s adaptability and plasticity without additional training or parameter costs. Extensive experimental results and further feature channel activations discussion on CIL benchmarks across six datasets validate the superior performance of our proposed method.

Keywords: class-incremental learning; continual learning; feature representation; stability and plasticity; catastrophic forgetting; pre-trained models (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/7/1095/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/7/1095/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:7:p:1095-:d:1621670

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().