@article{Liu2026, 
author = {Weike Liu and Cheng Zhu and Fan Wu and Lailong Luo and Zhaoyun Ding and Qingbao Liu},
title = {CEFCIL: Comprehensive Ensemble Framework for Exemplar-Free Class Incremental Learning},
year = {2026},
journal = {Big Data Mining and Analytics},
volume = {9},
number = {2},
pages = {481-499},
keywords = {Class Incremental Learning (CIL), ensemble framework, Mahalanobis metric},
url = {https://www.sciopen.com/article/10.26599/BDMA.2025.9020068},
doi = {10.26599/BDMA.2025.9020068},
abstract = {Catastrophic forgetting is currently the greatest challenge faced in Exemplar-Free Class Incremental Learning (EFCIL), which does not allow the replay of old data from previous tasks because of factors such as user privacy and device capacity limitations. In this paper, we propose a Comprehensive Ensemble Framework for exemplar-free Class Incremental Learning (CEFCIL), which includes an ensemble Nearest Class Mean (NCM) classifier based on the Mahalanobis metric with a given number of diversified base networks, a cached root model consisting of initialized base networks for root knowledge distillation, a dual knowledge distillation strategy, and a dimensional collapse prevention strategy. Across diverse experimental conditions, CEFCIL exhibits superior performance in EFCIL and possesses robust cross-domain capabilities.}
}