[论文解读] Exploiting Domain-Specific Features to Enhance Domain Generalization

Manh-Ha Bui, Toan Tran+2 more|arXiv (Cornell University)|Oct 18, 2021

Domain Adaptation and Few-Shot Learning被引用 69

一句话总结

本文提出 meta-Domain Specific-Domain Invariant (mDSDI)，一个框架，用以将领域不变特征与领域特定特征解耦，并使用元学习将领域特定信息适应到未见领域，在多个基准上实现具有竞争力的 DG 结果。

ABSTRACT

Domain Generalization (DG) aims to train a model, from multiple observed source domains, in order to perform well on unseen target domains. To obtain the generalization capability, prior DG approaches have focused on extracting domain-invariant information across sources to generalize on target domains, while useful domain-specific information which strongly correlates with labels in individual domains and the generalization to target domains is usually ignored. In this paper, we propose meta-Domain Specific-Domain Invariant (mDSDI) - a novel theoretically sound framework that extends beyond the invariance view to further capture the usefulness of domain-specific information. Our key insight is to disentangle features in the latent space while jointly learning both domain-invariant and domain-specific features in a unified framework. The domain-specific representation is optimized through the meta-learning framework to adapt from source domains, targeting a robust generalization on unseen domains. We empirically show that mDSDI provides competitive results with state-of-the-art techniques in DG. A further ablation study with our generated dataset, Background-Colored-MNIST, confirms the hypothesis that domain-specific is essential, leading to better results when compared with only using domain-invariant.

研究动机与目标

• 阐明仅学习领域不变表示在领域泛化中的局限性。
• 提出一个理论上有根据的框架，联合学习领域不变特征和领域特征。
• 使用元学习将源域中的领域特定信息适应到未见目标域。
• 解耦表征，以在稳健泛化过程中保留有用信息。
• 在标准 DG 基准测试和精心设计的消融数据集上评估 mDSDI，以验证领域特征的有用性。

提出的方法

• 在概率框架中定义领域不变与领域特征的潜在表示。
• 使用对抗训练在源域之间学习领域不变特征。
• 使用域分类器从每个源域学习领域特定特征。
• 通过最小化它们的协方差来强制 Z_I 与 Z_S 的解耦。
• 采用元学习程序将来自多个源域的领域特征适应到未见目标域。
• 端到端训练，结合不变性、特异性与元学习项的联合目标。

实验结果

研究问题

• RQ1 领域特定信息是否能在 DG 中超越领域不变表示提升泛化能力？
• RQ2 解耦领域不变与领域特征是否提高对未见域的鲁棒性？
• RQ3 元学习是否能够在没有目标数据的情况下有效地将领域特征适应到未见目标域？
• RQ4 与最先进方法相比，所提出框架在标准 DG 基准上的表现如何？

主要发现

方法	CMNIST	RMNIST	VLCS	PACS	OfficeHome	TerraInc.	DomainNet	Average
ERM (25)	51.5 ± 0.1	98.0 ± 0.0	77.5 ± 0.4	85.5 ± 0.2	66.5 ± 0.3	46.1 ± 1.8	40.9 ± 0.1	66.6
IRM (18)	52.0 ± 0.1	97.7 ± 0.1	78.5 ± 0.5	83.5 ± 0.8	64.3 ± 2.2	47.6 ± 0.8	33.9 ± 2.8	65.4
GroupDRO (26)	52.1 ± 0.0	98.0 ± 0.0	76.7 ± 0.6	84.4 ± 0.8	66.0 ± 0.7	43.2 ± 1.1	33.3 ± 0.2	64.8
Mixup (34;35;36)	52.1 ± 0.2	98.0 ± 0.1	77.4 ± 0.6	84.6 ± 0.6	68.1 ± 0.3	47.9 ± 0.8	39.2 ± 0.1	66.7
MLDG (11)	51.5 ± 0.1	97.9 ± 0.0	77.2 ± 0.4	84.9 ± 1.0	66.8 ± 0.6	47.7 ± 0.9	41.2 ± 0.1	66.7
CORAL (29)	51.5 ± 0.1	98.0 ± 0.1	78.8 ± 0.6	86.2 ± 0.3	68.7 ± 0.3	47.6 ± 1.0	41.5 ± 0.1	67.5
MMD (30)	51.5 ± 0.2	97.9 ± 0.0	77.5 ± 0.9	84.6 ± 0.5	66.3 ± 0.1	42.2 ± 1.6	23.4 ± 9.5	63.3
DANN (31)	51.5 ± 0.3	97.8 ± 0.1	78.6 ± 0.4	83.6 ± 0.4	65.9 ± 0.6	46.7 ± 0.5	38.3 ± 0.1	66.1
CDANN (32)	51.7 ± 0.1	97.9 ± 0.1	77.5 ± 0.1	82.6 ± 0.9	65.8 ± 1.3	45.8 ± 1.6	38.3 ± 0.3	65.6
MTL (1;27)	51.4 ± 0.1	97.9 ± 0.0	77.2 ± 0.4	84.6 ± 0.5	66.4 ± 0.5	45.6 ± 1.2	40.6 ± 0.1	66.2
SagNets (37)	51.7 ± 0.0	98.0 ± 0.0	77.8 ± 0.5	86.3 ± 0.2	68.1 ± 0.1	48.6 ± 1.0	40.3 ± 0.1	67.2
ARM (28)	56.2 ± 0.2	98.2 ± 0.1	77.6 ± 0.3	85.1 ± 0.4	64.8 ± 0.3	45.5 ± 0.3	35.5 ± 0.2	66.1
VREx (33)	51.8 ± 0.1	97.9 ± 0.1	78.3 ± 0.2	84.9 ± 0.6	66.4 ± 0.6	46.4 ± 0.6	33.6 ± 2.9	65.6
RSC (38)	51.7 ± 0.2	97.6 ± 0.1	77.1 ± 0.5	85.2 ± 0.9	65.5 ± 0.9	46.6 ± 1.0	38.9 ± 0.5	66.1
mDSDI (Ours)	52.2 ± 0.2	98.0 ± 0.1	79.0 ± 0.3	86.2 ± 0.2	69.2 ± 0.4	48.1 ± 1.4	42.8 ± 0.1	67.9

• mDSDI 在7个DG基准上实现了最高的平均准确率，相较于14个基线方法。
• mDSDI 在保持领域不变信息的同时，还利用领域特征在背景相关场景中提升性能。
• 在 VLCS 和 PACS 上，由于有效利用领域特征，mDSDI 显示出显著提升。
• mDSDI 在大规模 DomainNet（DomainNet 中 42.8%）和 Office-Home（69.2%）上取得强劲结果。
• 对 Background-Colored-MNIST 的消融验证表明，当背景提供标签相关线索时，领域特征有助于改进分类。