提出USP框架，同时提升半监督持续学习的无标签学习、稳定性与可塑性。
Divide-and-Conquer for Enhancing Unlabeled Learning, Stability, and Plasticity in Semi-supervised Continual Learning
- 分治策略分别优化无标签学习、稳定性和可塑性
- 最后准确率最高提升5.94%，显著优于现有方法
- 适合需要长期学习且标注成本高的场景
半监督持续学习（SSCL）旨在顺序学习中利用有标签和无标签数据，降低标注成本并应对持续到来的数据。其面临三大挑战：有效进行无标签学习（UL）、平衡记忆稳定性（MS）与学习可塑性（LP）。以往工作多聚焦于三者之一，本文提出USP框架，通过分治策略协同增强三者：(1) 特征空间预留（FSR）策略提升可塑性，通过将旧类别构造成等角紧框架，预留未来类别特征空间；(2) 分治伪标签（DCP）方法实现对高低置信度无标签数据的可靠伪标签分配；(3) 类均值锚定无标签蒸馏（CUD）增强稳定性，利用DCP输出将无标签数据锚定至稳定类均值进行蒸馏，防止遗忘。全面评估表明，USP在多个基准上超越现有方法，最后准确率最高提升5.94%，验证其有效性。代码已开源。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。