无需假设的持续学习新类检测方法
CONCLAD: COntinuous Novel CLAss Detector
- 通过迭代不确定性估计区分已知与新类样本
- 高置信度新类样本自动伪标注并更新模型
- 仅需少量人工标注即可持续识别新类别
在持续学习领域，依赖假设性‘预言者’进行新类检测虽常见但不现实。本文提出CONCLAD（COntinuous Novel CLAss Detector），解决部署后数据中持续新类检测这一未被充分探索的问题。每次新任务中，该方法采用迭代不确定性估计算法，区分已知类与新类样本，并进一步区分不同新类。高置信度预测为新类的样本将被自动伪标注并用于模型更新；同时，使用极小的监督预算迭代查询模糊的新类预测结果，这些结果也参与更新。在多个数据集、消融实验与设置下的评估表明，该方法能持续有效地分离新类与旧类样本。代码将在论文接受后公开。
原文摘要 · Abstract (English)
In the field of continual learning, relying on so-called oracles for novelty detection is commonplace albeit unrealistic. This paper introduces CONCLAD ("COntinuous Novel CLAss Detector"), a comprehensive solution to the under-explored problem of continual novel class detection in post-deployment data. At each new task, our approach employs an iterative uncertainty estimation algorithm to differentiate between known and novel class(es) samples, and to further discriminate between the different novel classes themselves. Samples predicted to be from a novel class with high-confidence are automatically pseudo-labeled and used to update our model. Simultaneously, a tiny supervision budget is used to iteratively query ambiguous novel class predictions, which are also used during update. Evaluation across multiple datasets, ablations and experimental settings demonstrate our method's effectiveness at separating novel and old class samples continuously. We will release our code upon acceptance.
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。