arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2210.02655cs.CV
收藏

基于对比因果学习的领域泛化

Domain Generalization via Contrastive Causal Learning

Zhejiang University(浙江大学)

Qiaowei Miao, Junkun Yuan, Kun Kuang

摘要:

领域泛化(DG)的目标是从一组源域中学习一个模型,该模型可以很好地泛化到看不见的目标域。基于不变因果机制的思想,人们一直致力于学习由对象决定但对领域变化不敏感的鲁棒因果效应。尽管因果效应具有不变性,但它们很难被量化和优化。受人类通过先验知识适应新环境的能力的启发,我们开发了一种新的对比因果模型(CCM),将看不见的图像转换为已知图像的特征,并量化基于已知知识的因果效应。考虑到DG中的域转移对转移的影响,我们提出了一个更具包容性的因果图来描述DG任务。基于此因果图,CCM控制域因子来切断多余的因果路径,并使用剩余部分通过前门准则来计算图像对标签的因果影响。具体来说,CCM由三个部分组成:(i)领域条件监督学习,它教导CCM图像和标签之间的相关性,(ii)因果效应学习,它帮助CCM测量图像对标签的真实因果效应,(iii)对比相似性学习,它聚类属于同一类的图像特征,并提供相似性的量化。最后,我们在多个数据集上测试了CCM的性能,包括PACS,THEOHOME和TerraIncognita。大量的实验表明,CCM优于以往的DG方法具有明显的优势。

英文摘要:

Domain Generalization (DG) aims to learn a model that can generalize well to unseen target domains from a set of source domains. With the idea of invariant causal mechanism, a lot of efforts have been put into learning robust causal effects which are determined by the object yet insensitive to the domain changes. Despite the invariance of causal effects, they are difficult to be quantified and optimized. Inspired by the ability that humans adapt to new environments by prior knowledge, We develop a novel Contrastive Causal Model (CCM) to transfer unseen images to taught knowledge which are the features of seen images, and quantify the causal effects based on taught knowledge. Considering the transfer is affected by domain shifts in DG, we propose a more inclusive causal graph to describe DG task. Based on this causal graph, CCM controls the domain factor to cut off excess causal paths and uses the remaining part to calculate the causal effects of images to labels via the front-door criterion. Specifically, CCM is composed of three components: (i) domain-conditioned supervised learning which teaches CCM the correlation between images and labels, (ii) causal effect learning which helps CCM measure the true causal effects of images to labels, (iii) contrastive similarity learning which clusters the features of images that belong to the same class and provides the quantification of similarity. Finally, we test the performance of CCM on multiple datasets including PACS, OfficeHome, and TerraIncognita. The extensive experiments demonstrate that CCM surpasses the previous DG methods with clear margins.

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。

↑