用置信度伪标签实现无监督增量学习，省去人工标注。
Unsupervised Incremental Learning Using Confidence-Based Pseudo-Labels
- 用置信度筛选伪标签，替代人工标注进行增量学习。
- 在CIFAR100和ImageNet100上达到接近有监督方法的性能。
- 适合数据标注成本高、资源受限的实际场景使用。
深度学习模型在多个计算机视觉任务中表现优异。但在现实场景中，训练时未见的新类别常会涌现，要求模型能持续学习新知识。类增量学习（CIL）方法可在保留旧知识的同时学习新类别，但其假设增量数据完全标注，这在现实中不成立。本文提出一种基于置信度的伪标签无监督增量学习方法（ICPL），以伪标签替代人工标注，实现从无标注数据中进行增量学习。将伪标签融入多种CIL方法，结合置信度筛选，在CIFAR100和ImageNet100上评估性能下降情况。与主流类增量新类别发现（class-iNCD）方法对比，结果显示，ICPL最终准确率超过当前最优class-iNCD方法5%以上。此外，方法在细粒度数据集上验证了实用性，并分析计算复杂度，证明其适用于资源受限环境。
原文摘要 · Abstract (English)
Deep learning models have achieved state-of-the-art performance in many computer vision tasks. However, in real-world scenarios, novel classes that were unseen during training often emerge, requiring models to acquire new knowledge incrementally. Class-Incremental Learning (CIL) methods enable a model to learn novel classes while retaining knowledge of previous classes. However, these methods make the strong assumption that the incremental dataset is fully labeled, which is unrealistic in practice. In this work, we propose an unsupervised Incremental Learning method using Confidence-based Pseudo-labels (ICPL), which replaces human annotations with pseudo-labels, enabling incremental learning from unlabeled datasets. We integrate these pseudo-labels into various CIL methods with confidence-based selection and evaluate performance degradation on CIFAR100 and ImageNet100. Then, we compare our approach to popular Class Incremental Novel Category Discovery (class-iNCD) methods addressing similar challenges. Additionally, we apply our method to fine-grained datasets to demonstrate its real-world practicality and measure its computational complexity to validate its suitability for resource-constrained environments. ICPL achieves competitive results compared to supervised methods and outperforms state-of-the-art class-iNCD methods by more than 5% in final accuracy.
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。