Incremental Image Classification Method Based on Integrated Transformer
IET Image Processing · 2026-01 · 20 (1)
DOI: 10.1049/ipr2.70506 ↗At a glance
Journal article in IET Image Processing, published online on 2026-11-03. Written by Yiliang Liu and 3 co-authors. 46 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: National Natural Science Foundation of China.
Abstract (original language)
In incremental learning scenarios, catastrophic forgetting remains a critical challenge when deploying neural networks under strict memory constraints and privacy‐preserving requirements. To address this issue, we propose a novel Transformer‐integrated framework (Boosting‐based Transformer Network (BT‐Net)) that effectively mitigates knowledge forgetting while maintaining classification performance. Our approach introduces two key components: one is a plug‐and‐play Transformer module that constructs a fusion dictionary bridging old and new feature representations, establishing inter‐task dependencies through attention mechanisms; the other is a SAMME‐inspired bootstrapping ensemble method that optimally combines predictions from both historical and current models. Extensive experiments conducted on CIFAR‐100 and ImageNet datasets for incremental learning demonstrate that the proposed method effectively alleviates catastrophic forgetting and improves model performance. The proposed method exhibits superior adaptability to real‐world scenarios with limited initial data.
Funding
- National Natural Science Foundation of China
Cite
APA
Liu, Y., Liu, H., Wang, Z., & Zhang, T. (2026). Incremental Image Classification Method Based on Integrated Transformer. IET Image Processing, 20(1). https://doi.org/10.1049/ipr2.70506
Vancouver
Liu Y, Liu H, Wang Z, Zhang T. Incremental Image Classification Method Based on Integrated Transformer. IET Image Processing. 2026;20(1). doi:10.1049/ipr2.70506
BibTeX
@article{Liu2026,
author = {Liu, Yiliang and Liu, Haonan and Wang, Zili and Zhang, Tong},
title = {Incremental Image Classification Method Based on Integrated Transformer},
journal = {IET Image Processing},
year = {2026},
volume = {20},
number = {1},
doi = {10.1049/ipr2.70506}
}
EUVIMED