DELTA：解耦长尾在线持续学习
DELTA: Decoupling Long-Tailed Online Continual Learning
AI总结：
针对长尾在线持续学习中的类别不平衡与灾难性遗忘问题，提出解耦方法 DELTA，结合监督对比学习与均衡损失平衡梯度，显著提升增量学习性能并超越现有 OCL 方法。
摘要：
实现普适人工智能的一项重大挑战是，在数据遵循长尾分布的真实场景中，模型快速学习新信息的能力有限，同时还要避免遗忘先前获得的知识。在本文中，我们研究了长尾在线持续学习（LTOCL）这一尚未得到充分探索的问题，其目标是从顺序到达的类别不平衡数据流中学习新任务。每条数据在训练中仅被观察一次，且事先不知道任务数据分布。我们提出了 DELTA，这是一种解耦学习方法，旨在增强学习表示并应对 LTOCL 中显著的不平衡问题。我们通过改造监督对比学习来吸引相似样本并排斥不相似（类别外）样本，从而增强学习过程。此外，通过在训练期间使用均衡损失平衡梯度，DELTA 显著提升了学习效果，并成功缓解了灾难性遗忘。通过广泛评估，我们证明 DELTA 提高了增量学习能力，超越了现有 OCL 方法。我们的结果表明，将 OCL 应用于真实世界应用具有相当大的前景。
英文摘要：
A significant challenge in achieving ubiquitous Artificial Intelligence is the limited ability of models to rapidly learn new information in real-world scenarios where data follows long-tailed distributions, all while avoiding forgetting previously acquired knowledge. In this work, we study the under-explored problem of Long-Tailed Online Continual Learning (LTOCL), which aims to learn new tasks from sequentially arriving class-imbalanced data streams. Each data is observed only once for training without knowing the task data distribution. We present DELTA, a decoupled learning approach designed to enhance learning representations and address the substantial imbalance in LTOCL. We enhance the learning process by adapting supervised contrastive learning to attract similar samples and repel dissimilar (out-of-class) samples. Further, by balancing gradients during training using an equalization loss, DELTA significantly enhances learning outcomes and successfully mitigates catastrophic forgetting. Through extensive evaluation, we demonstrate that DELTA improves the capacity for incremental learning, surpassing existing OCL methods. Our results suggest considerable promise for applying OCL in real-world applications.
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。
