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.
翻译:常规域通用 (CDG) 使用多标签源数据集来为未知目标域训练通用模型。 但是, 由于成本昂贵的注释成本, 标记所有源数据的要求很难在现实世界应用程序中达到 。 在本文中, 我们调查单标签标签域通用 (SLDG) 任务, 只有一个源域标签, 这比 CDG 任务更实际, 更具挑战性。 SLDG 任务中的一个主要障碍是偏差的过滤性一般偏差: 标签源数据集中的歧视性信息可能包含特定域的偏差, 限制经过培训的模型的多域化 。 为了应对这项具有挑战性的任务, 我们提议了一个名为 Dom- 隐性 Bislus 过滤 (DDBF) 的新框架, 将一个带有标签源数据标签的带有歧视性的模型, 然后将它特有的偏差与非标签源数据加以改进。 我们将过滤程序分为:(1) 通过基于 k 图像的分类模式的精选取性、 将Sqredual- drodualal dealalalalalation lagistration (S) laft Slab drogial drogistration) 和 Sq drovidudududududuisl drodudu 的Sm droduduisl disl disl disl disl disl 。