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 2007.06346cs.LGcs.CVstat.ML
收藏

自监督表示学习的白化算法

Whitening for Self-Supervised Representation Learning

University of Trento(特伦托大学);Department of Information Engineering and Computer Science (DISI)(信息工程与计算机科学系(DISI))

Aleksandr Ermolov, Aliaksandr Siarohin, Enver Sangineto, Nicu Sebe

摘要:

目前大多数的自监督表示学习(SSL)方法是基于对比损失和实例判别任务,其中同一图像实例的增强版本(“阳性”)与从其他图像中提取的实例(“阴性”)进行对比。为了使学习有效,许多负数应该与一个正数对进行比较,这需要计算。在本文中,我们提出了一个不同的方向和一个新的损失函数的SSL,这是基于白化的潜在空间的功能。白化操作对批处理样本具有“散射”效果,从而避免所有样本表示塌陷到单个点的退化解决方案。我们的解决方案不需要非对称网络,而且概念简单。此外,由于不需要底片,我们可以从同一图像实例中提取多个正对。该方法和所有实验的源代码可在https://github.com/htdt/self-supervised获得。

英文摘要:

Most of the current self-supervised representation learning (SSL) methods are based on the contrastive loss and the instance-discrimination task, where augmented versions of the same image instance ("positives") are contrasted with instances extracted from other images ("negatives"). For the learning to be effective, many negatives should be compared with a positive pair, which is computationally demanding. In this paper, we propose a different direction and a new loss function for SSL, which is based on the whitening of the latent-space features. The whitening operation has a "scattering" effect on the batch samples, avoiding degenerate solutions where all the sample representations collapse to a single point. Our solution does not require asymmetric networks and it is conceptually simple. Moreover, since negatives are not needed, we can extract multiple positive pairs from the same image instance. The source code of the method and of all the experiments is available at: https://github.com/htdt/self-supervised.

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。

↑