arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2010.07258cs.CV
收藏

表示学习的自监督排序

Self-Supervised Ranking for Representation Learning

KU Leuven(鲁汶大学);ETH Zurich(苏黎世联邦理工学院)

Ali Varamesh, Ali Diba, Tinne Tuytelaars, Luc Van Gool

摘要:

我们提出了一个新的框架,自监督表示学习,制定它作为一个排名问题,在图像检索上下文中的大量随机视图(增强)从图像中获得。我们的工作是基于两个直觉:第一,一个良好的图像表示必须产生一个高质量的图像排名在检索任务;第二,我们希望随机视图的图像排名更接近该图像的参考视图比其他图像的随机视图。因此,我们将表示学习建模为图像检索的学习排序问题。我们训练表示编码器通过最大化平均精度(AP)的排名,其中图像的随机视图被认为是正相关的,而其他图像被认为是负相关的。新的框架,被称为S2 R2,能够计算多个视图的全局目标,相比之下,在流行的对比学习框架,这是对视图计算的本地目标。原则上,通过使用排名标准,我们消除了对以对象为中心的策展数据集的依赖。当在STL 10和MS-COCO上训练时,S2 R2的性能优于Simplified和基于聚类的对比学习模型SwAV,同时在概念和实现上都要简单得多。在MS-COCO上,S2 R2的性能优于SwAV和Simplified,其裕度大于ST 110。这表明S2 R2在不同的场景中更有效,并且可以消除对以对象为中心的大型训练数据集的需求,以用于自监督表示学习。

英文摘要:

We present a new framework for self-supervised representation learning by formulating it as a ranking problem in an image retrieval context on a large number of random views (augmentations) obtained from images. Our work is based on two intuitions: first, a good representation of images must yield a high-quality image ranking in a retrieval task; second, we would expect random views of an image to be ranked closer to a reference view of that image than random views of other images. Hence, we model representation learning as a learning to rank problem for image retrieval. We train a representation encoder by maximizing average precision (AP) for ranking, where random views of an image are considered positively related, and that of the other images considered negatives. The new framework, dubbed S2R2, enables computing a global objective on multiple views, compared to the local objective in the popular contrastive learning framework, which is calculated on pairs of views. In principle, by using a ranking criterion, we eliminate reliance on object-centric curated datasets. When trained on STL10 and MS-COCO, S2R2 outperforms SimCLR and the clustering-based contrastive learning model, SwAV, while being much simpler both conceptually and at implementation. On MS-COCO, S2R2 outperforms both SwAV and SimCLR with a larger margin than on STl10. This indicates that S2R2 is more effective on diverse scenes and could eliminate the need for an object-centric large training dataset for self-supervised representation learning.

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。

↑