arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.12320cs.CVcs.LG
收藏

SCAN:学习无标签图像分类

SCAN: Learning to Classify Images without Labels

ETH Zurich(苏黎世联邦理工学院);KU Leuven(鲁汶大学)

Wouter Van Gansbeke, Simon Vandenhende, Stamatios Georgoulis, Marc Proesmans, Luc Van Gool

摘要:

当没有地面实况注释时,我们能自动将图像分组到语义上有意义的聚类中吗?无监督图像分类的任务仍然是计算机视觉中一个重要的、开放的挑战。最近的几种方法试图以端到端的方式解决这个问题。在本文中,我们偏离了最近的作品,并提倡一个两步的方法,特征学习和聚类解耦。首先,一个自我监督的任务,从表示学习获得语义有意义的功能。其次,我们使用获得的功能作为一个可学习的聚类方法的先验。在这样做的过程中,我们消除了集群学习依赖于低级特征的能力,这在当前的端到端学习方法中存在。实验评估表明,我们在分类精度方面优于最先进的方法,特别是CIFAR 10上的+26.6%,CIFAR 100 -20上的+25.0%和STL 10上的+21.3%。此外,我们的方法是第一个执行良好的大规模数据集的图像分类。特别是,我们在ImageNet上获得了有希望的结果,并且在不使用任何地面实况注释的情况下,在低数据状态下优于几种半监督学习方法。该守则可在https://github.com/wvangansbeke/Unsupervised-Classification上公开查阅。

英文摘要:

Can we automatically group images into semantically meaningful clusters when ground-truth annotations are absent? The task of unsupervised image classification remains an important, and open challenge in computer vision. Several recent approaches have tried to tackle this problem in an end-to-end fashion. In this paper, we deviate from recent works, and advocate a two-step approach where feature learning and clustering are decoupled. First, a self-supervised task from representation learning is employed to obtain semantically meaningful features. Second, we use the obtained features as a prior in a learnable clustering approach. In doing so, we remove the ability for cluster learning to depend on low-level features, which is present in current end-to-end learning approaches. Experimental evaluation shows that we outperform state-of-the-art methods by large margins, in particular +26.6% on CIFAR10, +25.0% on CIFAR100-20 and +21.3% on STL10 in terms of classification accuracy. Furthermore, our method is the first to perform well on a large-scale dataset for image classification. In particular, we obtain promising results on ImageNet, and outperform several semi-supervised learning methods in the low-data regime without the use of any ground-truth annotations. The code is made publicly available at https://github.com/wvangansbeke/Unsupervised-Classification.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑