arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.11702cs.CVcs.LG
收藏

无监督视觉表示的图像间不变性研究

Delving into Inter-Image Invariance for Unsupervised Visual Representations

Nanyang Technological University(南洋理工大学);The Chinese University of Hong Kong(香港中文大学)

Jiahao Xie, Xiaohang Zhan, Ziwei Liu, Yew Soon Ong, Chen Change Loy

摘要:

对比学习最近在无监督视觉表示学习中显示出巨大的潜力。现有的研究主要集中在图像内不变性学习。学习通常使用丰富的图像内变换来构建正对,然后使用对比损失来最大化一致性。相反,图像间不变性的优点仍然很少被探索。利用图像间不变性的一个主要障碍是不清楚如何可靠地构建图像间正对,并且由于没有对注释可用,因此还不清楚如何从它们中得到有效的监督。在这项工作中,我们提出了一个全面的实证研究,以更好地了解图像间不变性学习的作用,从三个主要组成部分:伪标签维护,采样策略,和决策边界设计。为了便于研究,我们引入了一个统一的通用框架,支持无监督的图像内和图像间不变性学习的集成。通过精心设计的比较和分析,揭示了多个有价值的观察结果:1)在线标签收敛速度更快,性能优于离线标签; 2)半硬负样本比硬负样本更可靠和无偏; 3)不太严格的决策边界更有利于图像间不变性学习。通过所有获得的配方,我们的最终模型,即Interceptor,在多个标准基准上显示出对最先进的图像内不变性学习方法的一致改进。我们希望这项工作将提供有用的经验,设计有效的无监督图像间不变性学习。代码:https://github.com/open-mmlab/mmselfsup.

英文摘要:

Contrastive learning has recently shown immense potential in unsupervised visual representation learning. Existing studies in this track mainly focus on intra-image invariance learning. The learning typically uses rich intra-image transformations to construct positive pairs and then maximizes agreement using a contrastive loss. The merits of inter-image invariance, conversely, remain much less explored. One major obstacle to exploit inter-image invariance is that it is unclear how to reliably construct inter-image positive pairs, and further derive effective supervision from them since no pair annotations are available. In this work, we present a comprehensive empirical study to better understand the role of inter-image invariance learning from three main constituting components: pseudo-label maintenance, sampling strategy, and decision boundary design. To facilitate the study, we introduce a unified and generic framework that supports the integration of unsupervised intra- and inter-image invariance learning. Through carefully-designed comparisons and analysis, multiple valuable observations are revealed: 1) online labels converge faster and perform better than offline labels; 2) semi-hard negative samples are more reliable and unbiased than hard negative samples; 3) a less stringent decision boundary is more favorable for inter-image invariance learning. With all the obtained recipes, our final model, namely InterCLR, shows consistent improvements over state-of-the-art intra-image invariance learning methods on multiple standard benchmarks. We hope this work will provide useful experience for devising effective unsupervised inter-image invariance learning. Code: https://github.com/open-mmlab/mmselfsup.

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。

↑