用视觉Transformer和流形学习实现无需标注的开放世界聚类，性能达新高。
Dimensionally Reduced Open-World Clustering: DROWCULA
- 基于ViT注意力机制生成嵌入，结合流形学习优化数据几何结构
- 在CIFAR-10/100、ImageNet-100、Tiny ImageNet上刷新单模态聚类与新类发现性能
- 无需预知类别数，完全无监督，适合真实场景中未知类别的发现
标注数据是监督学习的基础，但人工标注代价高昂。许多现实应用面临挑战：即使已知任务中的类别，未来仍可能出现新类别。以往研究多聚焦于半监督方法。本文提出一种全新的全无监督方法，用于在图像分类任务中识别新类别。该方法利用视觉Transformer（ViT）的注意力机制生成向量嵌入，并通过流形学习技术挖掘数据内在几何结构，优化嵌入表示以提升聚类效果。实验表明，在CIFAR-10、CIFAR-100、ImageNet-100和Tiny ImageNet上，无论类别数是否预先已知，本方法均在单模态聚类与新类发现任务中达到新最佳性能。代码已开源：https://github.com/DROWCULA/DROWCULA。
原文摘要 · Abstract (English)
Working with annotated data is the cornerstone of supervised learning. Nevertheless, providing labels to instances is a task that requires significant human effort. Several critical real-world applications make things more complicated because no matter how many labels may have been identified in a task of interest, it could be the case that examples corresponding to novel classes may appear in the future. Not unsurprisingly, prior work in this, so-called, `open-world' context has focused a lot on semi-supervised approaches. Focusing on image classification, somehow paradoxically, we propose a fully unsupervised approach to the problem of determining the novel categories in a particular dataset. Our approach relies on estimating the number of clusters using Vision Transformers, which utilize attention mechanisms to generate vector embeddings. Furthermore, we incorporate manifold learning techniques to refine these embeddings by exploiting the intrinsic geometry of the data, thereby enhancing the overall image clustering performance. Overall, we establish new State-of-the-Art results on single-modal clustering and Novel Class Discovery on CIFAR-10, CIFAR-100, ImageNet-100, and Tiny ImageNet. We do so, both when the number of clusters is known or unknown ahead of time. The code is available at: https://github.com/DROWCULA/DROWCULA.
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。