Conditional Adversarial Domain Adaptation
Adversarial learning has been embedded into deep networks to learn disentangled and transferable representations for domain adaptation. Existing adversarial domain adaptation methods may not effectively align different domains of multimodal distributions native in classification problems. In this paper, we present conditional adversarial domain adaptation, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions. Conditional domain adversarial networks (CDANs) are designed with two novel conditioning strategies: multilinear conditioning that captures the cross-covariance between feature representations and classifier predictions to improve the discriminability, and entropy conditioning that controls the uncertainty of classifier predictions to guarantee the transferability. With theoretical guarantees and a few lines of codes, the approach has exceeded state-of-the-art results on five datasets.
Code (5)
Tasks
Domain AdaptationGeneral ClassificationSimilar Papers 제목 키워드 기반
Multi-source Heterogeneous Domain Adaptation with Conditional Weighting Adversarial Network
Heterogeneous domain adaptation (HDA) tackles the learning of cross-domain samples with both different probability distributions and feature representations. Most of the existing HDA studies focus on the single-source sc…
Domain AdaptationAdversarial Unsupervised Domain Adaptation with Conditional and Label Shift: Infer, Align and Iterate
In this work, we propose an adversarial unsupervised domain adaptation (UDA) approach with the inherent conditional and label shifts, in which we aim to align the distributions w.r.t. both $p(x|y)$ and $p(y)$. Since the …
Domain AdaptationUnsupervised Domain AdaptationCycle-consistent Conditional Adversarial Transfer Networks
Domain adaptation investigates the problem of cross-domain knowledge transfer where the labeled source domain and unlabeled target domain have distinctive data distributions. Recently, adversarial training have been succ…
Domain AdaptationTransfer LearningSelf-adaptive Re-weighted Adversarial Domain Adaptation
Existing adversarial domain adaptation methods mainly consider the marginal distribution and these methods may lead to either under transfer or negative transfer. To address this problem, we present a self-adaptive re-we…
Domain AdaptationTripletDiscriminative Active Learning for Domain Adaptation
Domain Adaptation aiming to learn a transferable feature between different but related domains has been well investigated and has shown excellent empirical performances. Previous works mainly focused on matching the marg…
Active LearningDiversityDomain Adaptation