文献类型：期刊文献

英文题名：Bamboo: A Novel Session-Aware Framework With Equiangular Tight Frame Prototypes for Few-Shot Class-Incremental Learning

作者：Lu, Xuehan[1,2];Wang, Zhe[1,2];Fu, Zhiling[1,2];Xu, Xinlei[1,2];Zhang, Qian[1,2];Xiao, Ting[1,2];Du, Wenli[3]

机构：[1]East China Univ Sci & Technol, Key Lab Smart Mfg Energy Chem Proc, Minist Educ, Shanghai 200237, Peoples R China;[2]East China Univ Sci & Technol, Dept Comp Sci & Engn, Shanghai 200237, Peoples R China;[3]Minist Educ, Key Lab Smart Mfg Energy Chem Proc, Shanghai 200237, Peoples R China

年份：2025

外文期刊名：IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS

收录：;EI(收录号：20254619512360);WOS:【SCI-EXPANDED(收录号:WOS:001616581700001)】；

基金：This work was supported in part by the National Natural Science Foundation of China under Grant 62476087 and Grant 62201341; in part by Shanghai Municipal Education Commission's Initiative on Artificial Intelligence-Driven Reform of Scientific Research Paradigms and Empowerment of Discipline Leapfrogging, National Key Research and Development Program of China, under Grant 2022YFB3203500; and in part by the Special Fund for Basic Scientific Research Operations in Central Universities.

语种：英文

外文关键词：Bamboo; Power capacitors; Semantics; Prototypes; Incremental learning; Training; Few shot learning; Standards; Smart manufacturing; Learning systems; Equiangular tight frame (ETF); few-shot class-incremental learning (FSCIL); prototype learning

摘要：Few-shot class-incremental learning (FSCIL) presents a greater challenge compared with few-shot task-incremental learning (FSTIL) due to the need to classify all previous classes without prior knowledge of the session identifier (session-ID). To address this, we propose Bamboo, a novel framework for FSCIL that introduces a cascading inference mechanism to explicitly infer the session-ID for each sample. This mechanism is enabled by a novel, session-specific equiangular tight frame prototype (ETF-P) classifier. By adaptively fusing session-agnostic and session-specific semantics, the ETF-P classifier reliably determines if a sample belongs to its associated session, which is the core decision required at each step of the cascade. Considering the incremental nature of the learning process, which resembles the continuous growth of bamboo, we treat the base session classifier as the foundational bamboo node and progressively add new session classifiers as additional nodes on top. During the testing phase, each sample flows sequentially through the bamboo nodes, from top to bottom, to determine its session-ID and to be classified accordingly. Overall, the Bamboo framework is capable of perceiving session-ID without prior knowledge and classifying each sample within the correct session, leading to state-of-the-art performance on multiple benchmark datasets.