提出COUQ方法，让AI在无标签数据中持续识别新类别并评估不确定性。
Uncertainty Quantification in Continual Open-World Learning
- 基于迭代不确定性估计，适应不断出现的未知数据。
- 在多个数据集上优于现有最优方法，支持主动学习与半监督学习。
- 适合部署于真实世界、需持续学习的新场景，如机器人或自动驾驶。
实际应用中的AI应能自主应对部署后遇到的新情况。然而，在持续学习领域，依赖新颖性检测和标注探针的做法虽常见却不现实。本文针对一个关键且研究不足的问题：部署后的AI持续接收未标注数据——可能包含已知类别的新样本或未知类别的新样本——必须持续适应。为此，我们提出方法COUQ（Continual Open-world Uncertainty Quantification），一种专为广义持续开放世界多分类场景设计的迭代不确定性估计算法。我们在持续开放世界的关键子任务上严格验证并评估COUQ：持续新颖性检测、不确定性引导的主动学习，以及半监督持续学习中的伪标签生成。实验表明，COUQ在多个数据集、不同模型主干网络下均表现优异，性能超越现有最先进方法。
原文摘要 · Abstract (English)
AI deployed in the real-world should be capable of autonomously adapting to novelties encountered after deployment. Yet, in the field of continual learning, the reliance on novelty and labeling oracles is commonplace albeit unrealistic. This paper addresses a challenging and under-explored problem: a deployed AI agent that continuously encounters unlabeled data - which may include both unseen samples of known classes and samples from novel (unknown) classes - and must adapt to it continuously. To tackle this challenge, we propose our method COUQ "Continual Open-world Uncertainty Quantification", an iterative uncertainty estimation algorithm tailored for learning in generalized continual open-world multi-class settings. We rigorously apply and evaluate COUQ on key sub-tasks in the Continual Open-World: continual novelty detection, uncertainty guided active learning, and uncertainty guided pseudo-labeling for semi-supervised CL. We demonstrate the effectiveness of our method across multiple datasets, ablations, backbones and performance superior to state-of-the-art.
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。