arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2006.11480cs.CV
收藏

面向深度表示学习的无监督图像分类

Unsupervised Image Classification for Deep Representation Learning

Hikvision Research Institute(海康威视研究院);South China University of Technology(华南理工大学)

Weijie Chen, Shiliang Pu, Di Xie, Shicai Yang, Yilu Guo, Luojun Lin

摘要:

针对自监督学习的深度聚类是无监督视觉表示学习的一个非常重要和有前途的方向,因为它需要很少的领域知识来设计借口任务。然而,嵌入聚类的关键部分,限制了它的扩展到超大规模的数据集,由于其先决条件,以保存整个数据集的全局潜在嵌入。在这项工作中,我们的目标是使这个框架更加简单和优雅的性能下降。我们提出了一个不使用嵌入聚类的无监督图像分类框架,这与标准的监督训练方式非常相似。为了详细解释,我们进一步分析了它与深度聚类和对比学习的关系。在ImageNet数据集上进行了大量的实验,以证明我们的方法的有效性。此外,在迁移学习基准上的实验也验证了该算法在多标签图像分类、目标检测、语义分割和Few-Shot图像分类等后续任务中的推广性。

英文摘要:

Deep clustering against self-supervised learning is a very important and promising direction for unsupervised visual representation learning since it requires little domain knowledge to design pretext tasks. However, the key component, embedding clustering, limits its extension to the extremely large-scale dataset due to its prerequisite to save the global latent embedding of the entire dataset. In this work, we aim to make this framework more simple and elegant without performance decline. We propose an unsupervised image classification framework without using embedding clustering, which is very similar to standard supervised training manner. For detailed interpretation, we further analyze its relation with deep clustering and contrastive learning. Extensive experiments on ImageNet dataset have been conducted to prove the effectiveness of our method. Furthermore, the experiments on transfer learning benchmarks have verified its generalization to other downstream tasks, including multi-label image classification, object detection, semantic segmentation and few-shot image 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。

↑