arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.02598cs.LGcs.CV
收藏

汇集具有多重协变量偏移与不平衡的图像数据集

Pooling Image Datasets With Multiple Covariate Shift and Imbalance

UW-Madison(威斯康星大学麦迪逊分校)

Sotirios Panagiotis Chytas, Vishnu Suresh Lokhande, Peiran Li, Vikas Singh

AI总结:

针对跨机构图像数据集汇集中的多重协变量偏移与不平衡问题,本文基于范畴论提出一种简单有效的解决方案,避免了复杂的多阶段训练流程,并在真实数据集上验证了其有效性,同时为5+种问题设置提供了统一视角。

摘要:

小样本量在许多学科中很常见,这促使需要跨多个机构汇集大致相似的数据集,以研究图像与疾病结果之间微弱但相关的关联。此类数据通常在协变量(即次要的非图像数据)中表现出偏移/不平衡。在标准统计分析中控制此类干扰变量很常见,但这些想法不能直接应用于过参数化模型。因此,最近的工作展示了不变表示学习的策略如何提供一个有意义的起点,但目前的方法仅限于一次仅考虑几个协变量的偏移/不平衡。在本文中,我们展示了如何从范畴论的角度看待这个问题,提供了一个简单有效的解决方案,完全避免了原本所需的复杂多阶段训练流程。我们通过在真实数据集上的大量实验展示了该方法的有效性。此外,我们讨论了这种表述方式如何为至少5+种不同问题设置提供统一视角,从自监督学习到3D重建中的匹配问题。

英文摘要:

Small sample sizes are common in many disciplines, which necessitates pooling roughly similar datasets across multiple institutions to study weak but relevant associations between images and disease outcomes. Such data often manifest shift/imbalance in covariates (i.e., secondary non-imaging data). Controlling for such nuisance variables is common within standard statistical analysis, but the ideas do not directly apply to overparameterized models. Consequently, recent work has shown how strategies from invariant representation learning provides a meaningful starting point, but the current repertoire of methods is limited to accounting for shifts/imbalances in just a couple of covariates at a time. In this paper, we show how viewing this problem from the perspective of Category theory provides a simple and effective solution that completely avoids elaborate multi-stage training pipelines that would otherwise be needed. We show the effectiveness of this approach via extensive experiments on real datasets. Further, we discuss how this style of formulation offers a unified perspective on at least 5+ distinct problem settings, from self-supervised learning to matching problems in 3D reconstruction.

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。

↑