用伪标签提升小样本下的层级开放集分类性能
Semi-Supervised Hierarchical Open-Set Classification
- 基于师生框架与子树伪标签，有效利用含未知类的无标注数据
- 仅需每类20个标注样本，就达到全监督模型水平
- 适合标注稀缺但数据量大的开放场景，如自然物种识别
层级开放集分类通过将未见类别归入类别层级中合适的高层类别来处理。本文将其拓展至半监督设置，使大规模、未清理的数据集（包含已知与未知类别混合）可用于提升性能。提出一种基于伪标签的师生框架，引入两个关键组件：1）子树伪标签，在存在未知数据时提供可靠监督；2）年龄门控机制，缓解伪标签的过自信问题。实验表明，该框架优于自监督预训练后微调的方法，且在iNaturalist19数据集上仅使用每类20个标注样本时，即可达到全监督模型性能。代码已开源。
原文摘要 · Abstract (English)
Hierarchical open-set classification handles previously unseen classes by assigning them to the most appropriate high-level category in a class taxonomy. We extend this paradigm to the semi-supervised setting, enabling the use of large-scale, uncurated datasets containing a mixture of known and unknown classes to improve the hierarchical open-set performance. To this end, we propose a teacher-student framework based on pseudo-labeling. Two key components are introduced: 1) subtree pseudo-labels, which provide reliable supervision in the presence of unknown data, and 2) age-gating, a mechanism that mitigates overconfidence in pseudo-labels. Experiments show that our framework outperforms self-supervised pretraining followed by supervised adaptation, and even matches the fully supervised counterpart when using only 20 labeled samples per class on the iNaturalist19 benchmark. Our code is available at https://github.com/walline/semihoc.
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。