通过剪裁特定标签区域实现高效持续学习，解决遗忘与标签缺失问题。
Cut out and Replay: A Simple yet Versatile Strategy for Multi-Label Online Continual Learning
- 基于输入数据结构识别标签相关区域，精细定位并剪裁强化。
- 在多个图像数据集上显著缓解遗忘、缺失标签与类别不平衡问题。
- 方法简单通用，可无缝集成到现有持续学习框架中，适合研究者使用。
多标签在线持续学习（MOCL）要求模型从无限的多标签数据流中持续学习，面临灾难性遗忘、潜在标签缺失及不可控类别分布不均等复杂挑战。现有方法虽尝试通过多种技术应对，但普遍忽略标签特异性区域的识别与特征学习——这是多标签学习中的根本性解决方案，却在增量且部分监督的在线设置下难以实现。为此，我们首先利用输入数据的内在结构信息，评估并验证不同预训练模型的天然定位能力。随后提出 CUTER（Cut-out-and-Experience-Replay），一种简单而通用的策略：通过进一步识别、增强并剪裁标签特异性区域，为经验回放提供细粒度监督信号。该方法不仅同时缓解灾难性遗忘、标签缺失与类别不平衡问题，还可作为正交方案无缝融入现有方法。在多个多标签图像基准上的大量实验表明其优越性。代码已开源。
原文摘要 · Abstract (English)
Multi-Label Online Continual Learning (MOCL) requires models to learn continuously from endless multi-label data streams, facing complex challenges including persistent catastrophic forgetting, potential missing labels, and uncontrollable imbalanced class distributions. While existing MOCL methods attempt to address these challenges through various techniques, \textit{they all overlook label-specific region identifying and feature learning} - a fundamental solution rooted in multi-label learning but challenging to achieve in the online setting with incremental and partial supervision. To this end, we first leverage the inherent structural information of input data to evaluate and verify the innate localization capability of different pre-trained models. Then, we propose CUTER (CUT-out-and-Experience-Replay), a simple yet versatile strategy that provides fine-grained supervision signals by further identifying, strengthening and cutting out label-specific regions for efficient experience replay. It not only enables models to simultaneously address catastrophic forgetting, missing labels, and class imbalance challenges, but also serves as an orthogonal solution that seamlessly integrates with existing approaches. Extensive experiments on multiple multi-label image benchmarks demonstrate the superiority of our proposed method. The code is available at \href{https://github.com/wxr99/Cut-Replay}{https://github.com/wxr99/Cut-Replay}
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。