面向模糊监督的鲁棒增量学习研究
Towards Robust Incremental Learning under Ambiguous Supervision
AI总结：
本文提出增量偏标签学习范式及原型引导消歧与回放算法PGDR，利用类别原型、动量伪标签和记忆回放同时解决标签模糊与灾难性遗忘问题，实验验证其优越性。
摘要：
传统增量学习（IL）旨在处理顺序出现的全监督学习问题，其中新类别会不时出现。然而，由于固有的标注不确定性和模糊性，在动态学习系统中收集高质量标注数据的成本可能极其高昂。为缓解这一问题，我们提出了一种新颖的弱监督学习范式，称为增量偏标签学习（IPLL），其中顺序到达的数据关联的是一组候选标签而非真实标签。在技术层面，我们开发了原型引导消歧与回放算法（PGDR），该算法利用类别原型作为代理来缓解IPLL中的两个相互交织的挑战，即标签模糊性和灾难性遗忘。针对前者，PGDR封装了一种基于动量的伪标签算法以及原型引导初始化，从而实现对类别的均衡感知。为减轻遗忘，我们开发了一种记忆回放技术，该技术在收集已充分消歧样本的同时保持代表性和多样性。通过联合蒸馏来自精心整理的记忆数据中的知识，我们的框架对新任务样本展现出强大的消歧能力，并实现了更少的知识遗忘。大量实验表明，PGDR取得了优越的性能。
英文摘要：
Traditional Incremental Learning (IL) targets to handle sequential fully-supervised learning problems where novel classes emerge from time to time. However, due to inherent annotation uncertainty and ambiguity, collecting high-quality annotated data in a dynamic learning system can be extremely expensive. To mitigate this problem, we propose a novel weakly-supervised learning paradigm called Incremental Partial Label Learning (IPLL), where the sequentially arrived data relate to a set of candidate labels rather than the ground truth. Technically, we develop the Prototype-Guided Disambiguation and Replay Algorithm (PGDR) which leverages the class prototypes as a proxy to mitigate two intertwined challenges in IPLL, i.e., label ambiguity and catastrophic forgetting. To handle the former, PGDR encapsulates a momentum-based pseudo-labeling algorithm along with prototype-guided initialization, resulting in a balanced perception of classes. To alleviate forgetting, we develop a memory replay technique that collects well-disambiguated samples while maintaining representativeness and diversity. By jointly distilling knowledge from curated memory data, our framework exhibits a great disambiguation ability for samples of new tasks and achieves less forgetting of knowledge. Extensive experiments demonstrate that PGDR achieves superior
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。
