arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2110.00726cs.CV
收藏

单标记领域泛化中的领域特定偏置过滤

Domain-Specific Bias Filtering for Single Labeled Domain Generalization

Zhejiang University(浙江大学)

Junkun Yuan, Xu Ma, Defang Chen, Kun Kuang, Fei Wu, Lanfen Lin

摘要:

传统领域泛化(CDG)利用多个标记的源数据集来训练一个不可见目标领域的可泛化模型。然而,由于昂贵的标注成本,标注所有源数据的要求很难满足在现实世界中的应用。在本文中,我们研究了一个单一的标记领域泛化(SLDG)任务,只有一个源域被标记,这是更实际和更具挑战性的CDG任务。SLDG任务中的一个主要障碍是区分度-泛化偏差:标记源数据集中的区分信息可能包含特定领域的偏差,从而限制了训练模型的泛化。为了解决这个具有挑战性的任务,我们提出了一个新的框架称为特定领域的偏见过滤(DSBF),它与标记的源数据的歧视性模型,然后过滤掉其特定领域的偏见与未标记的源数据的泛化改进。我们将过滤过程分为(1)通过基于k-means聚类的语义特征重新提取的特征提取器去偏置和(2)通过注意力引导的语义特征投影的分类器校正。DSBF统一了对标记和未标记源数据的探索,以增强训练模型的可区分性和泛化性,从而产生高度泛化的模型。我们进一步提供理论分析,以验证所提出的特定领域的偏置滤波过程。在多个数据集上进行的大量实验表明,DSBF在处理具有挑战性的SLDG任务和CDG任务方面表现出色。

英文摘要:

Conventional Domain Generalization (CDG) utilizes multiple labeled source datasets to train a generalizable model for unseen target domains. However, due to expensive annotation costs, the requirements of labeling all the source data are hard to be met in real-world applications. In this paper, we investigate a Single Labeled Domain Generalization (SLDG) task with only one source domain being labeled, which is more practical and challenging than the CDG task. A major obstacle in the SLDG task is the discriminability-generalization bias: the discriminative information in the labeled source dataset may contain domain-specific bias, constraining the generalization of the trained model. To tackle this challenging task, we propose a novel framework called Domain-Specific Bias Filtering (DSBF), which initializes a discriminative model with the labeled source data and then filters out its domain-specific bias with the unlabeled source data for generalization improvement. We divide the filtering process into (1) feature extractor debiasing via k-means clustering-based semantic feature re-extraction and (2) classifier rectification through attention-guided semantic feature projection. DSBF unifies the exploration of the labeled and the unlabeled source data to enhance the discriminability and generalization of the trained model, resulting in a highly generalizable model. We further provide theoretical analysis to verify the proposed domain-specific bias filtering process. Extensive experiments on multiple datasets show the superior performance of DSBF in tackling both the challenging SLDG task and the CDG task.

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。

↑