Adversarial Domain Adaptation with Domain Mixup

By Minghao Xu, Jian Zhang, Bingbing Ni, Teng Li, Chengjie Wang, Qi Tian, Wenjun Zhang. 2019

509 citations recorded by the source corpus.

Recent works on domain adaptation reveal the effectiveness of adversarial learning on filling the discrepancy between source and target domains. However, two common limitations exist in current adversarial-learning-based methods. First, samples from two domains alone are not sufficient to ensure domain-invariance at most part of latent space. Second, the domain discriminator involved in these methods can only judge real or fake with the guidance of hard label, while it is more reasonable to use soft scores to evaluate the generated images or features, i.e., to fully utilize the inter-domain information. In this paper, we present adversarial domain adaptation with domain mixup (DM-ADA), which guarantees domain-invariance in a more continuous latent space and guides the domain discriminator in judging samples' difference relative to source and target domains. Domain mixup is jointly conducted on pixel and feature level to improve the robustness of models. Extensive experiments prove that the proposed approach can achieve superior performance on tasks with various degrees of domain shift and data complexity.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

In Search of Lost Domain Generalization (2020, background): “• Inter-domain Mixup ( Mixup , Xu et al. [2019], Yan et al. [2020], Wang et al. [2020]) performs ERM on linear interpolations of examples from random pairs of domains and their labels.”
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization (2021, methodology): “Inter-domain mixup [45, 44, 43] techniques are introduced to perform empirical risk minimization on linearly interpolated examples from random pairs across domains.”
FixBi: Bridging Domain Spaces for Unsupervised Domain Adaptation (2020, methodology): “Recent works [10, 35, 38, 24, 8, 37, 31, 43] have focused on UDA based on domain alignment and discriminative domain-invariant feature learning methods.”
MetaCorrection: Domain-aware Meta Loss Correction for Unsupervised Domain Adaptation in Semantic Segmentation (2021, unknown): “On one hand, adversarial learning based UDA methods as a dominant stream have been devised to bridge the domain gap by aligning the distributions of two domains in the appearance [6, 7, 9, 22], feature [2, 11, 39, 45] or output spaces [20, 26, 40, 41].”
A Review of Single-Source Deep Unsupervised Visual Domain Adaptation (2020, background): “[66] explored two common limitations in current adversarial-based methods.”
Test-Time Classifier Adjustment Module for Model-Agnostic Domain Generalization (2021, methodology): “These results include the following algorithms: Empirical Risk Minimization (ERM), Group Distributionally Robust Optimization (GroupDRO) [41], Inter-domain Mixup (Mixup) [56, 58, 53], Meta-Learning for Domain Generalization (MLDG) [28], DomainAdversarial Neural Networks (DANN) [15], Class-conditiona”
Domain Generalization using Causal Matching (2020, methodology): “(Carlucci et al., 2019), S-MLDG (Li et al., 2020), D-SAM (D’Innocente & Caputo, 2018), MMLD (Matsuura & Harada, 2020), DDAIG (Zhou et al., 2020) SagNet (Nam et al., 2019), DDEC (Asadi et al., 2019), DANN (Ganin et al., 2016), C-DANN (Li et al., 2018d), DRO (Sagawa et al., 2019), Mixup (Xu et al., 20”