在标注模糊时仍能稳定增量学习，提升模型鲁棒性。
Towards Robust Incremental Learning under Ambiguous Supervision
- 用原型引导去歧义和重放机制应对标签模糊问题
- 新任务上准确率提升12.3%，遗忘率降低至15.6%
- 适合数据标注不全的现实场景，如医疗图像增量学习
传统增量学习假设数据具有完整监督信息，但在动态系统中，标注存在固有不确定性与模糊性，高质量标注成本高昂。为此，本文提出一种新型弱监督学习范式——增量部分标签学习（IPLL），其中新到达的数据仅关联一组候选标签而非真实标签。技术上，提出原型引导去歧义与重放算法（PGDR），利用类别原型作为代理，同时缓解标签模糊与灾难性遗忘两大挑战。为处理前者，PGDR结合基于动量的伪标签算法与原型引导初始化，实现类别的均衡感知；为缓解遗忘，设计记忆重放机制，保留已去歧义样本，并保持代表性与多样性。通过联合蒸馏精选记忆数据，框架在新任务上展现出强去歧义能力，且知识遗忘显著减少。大量实验表明，PGDR在多个数据集上均优于现有方法，平均准确率提升12.3%，遗忘率降至15.6%。
原文摘要 · Abstract (English)
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
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。