分而治之：增强半监督持续学习中的无标签学习、稳定性和可塑性
Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
AI总结：
提出USP分而治之框架，通过特征空间预留、分而治之伪标签和类均值锚定蒸馏，协同增强半监督持续学习中的可塑性、无标签学习和稳定性，最后准确率提升达5.94%。
摘要：
半监督持续学习（SSCL）旨在顺序学习设置中利用有标签和无标签数据，旨在降低标注成本的同时管理持续到达的数据。SSCL引入了复杂的挑战，包括确保有效的无标签学习（UL），同时平衡记忆稳定性（MS）和学习可塑性（LP）。以往SSCL工作通常只关注这三方面的孤立方面，而本工作提出了USP，一个分而治之框架，旨在协同增强这三个方面：（1）用于LP的特征空间预留（FSR）策略，通过将旧类塑造成等角紧框架来为未来类构建预留特征位置；（2）用于UL的分而治之伪标签（DCP）方法，为高置信度和低置信度的无标签数据分配可靠的伪标签；（3）用于MS的类均值锚定无标签蒸馏（CUD），重用DCP的输出将无标签数据锚定到稳定的类均值以进行蒸馏，防止遗忘。综合评估表明，USP优于先前的SSCL方法，在最后准确率上最高提升5.94%，验证了其有效性。代码可在https://github.com/NJUyued/USP4SSCL获取。
英文摘要：
Semi-supervised continual learning (SSCL) seeks to leverage both labeled and unlabeled data in a sequential learning setup, aiming to reduce annotation costs while managing continual data arrival. SSCL introduces complex challenges, including ensuring effective unlabeled learning (UL), while balancing memory stability (MS) and learning plasticity (LP). Previous SSCL efforts have typically focused on isolated aspects of the three, while this work presents USP, a divide-and-conquer framework designed to synergistically enhance these three aspects: (1) Feature Space Reservation (FSR) strategy for LP, which constructs reserved feature locations for future classes by shaping old classes into an equiangular tight frame; (2) Divide-and-Conquer Pseudo-labeling (DCP) approach for UL, which assigns reliable pseudo-labels across both high- and low-confidence unlabeled data; and (3) Class-mean-anchored Unlabeled Distillation (CUD) for MS, which reuses DCP's outputs to anchor unlabeled data to stable class means for distillation to prevent forgetting. Comprehensive evaluations show USP outperforms prior SSCL methods, with gains up to 5.94% in the last accuracy, validating its effectiveness. The code is available at https://github.com/NJUyued/USP4SSCL.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
