Corpus ID: 209832406

Improve Unsupervised Domain Adaptation with Mixup Training

@article{Yan2020ImproveUD,
  title={Improve Unsupervised Domain Adaptation with Mixup Training},
  author={Shen Yan and Huan Song and Nanxiang Li and Lincan Zou and Liu Ren},
  journal={ArXiv},
  year={2020},
  volume={abs/2001.00677}
}
Unsupervised domain adaptation studies the problem of utilizing a relevant source domain with abundant labels to build predictive modeling for an unannotated target domain. Recent work observe that the popular adversarial approach of learning domain-invariant features is insufficient to achieve desirable target domain performance and thus introduce additional training constraints, e.g. cluster assumption. However, these approaches impose the constraints on source and target domains individually… Expand
Adversarially Constrained Interpolation for Unsupervised Domain Adaptation
TLDR
This work addresses the problem of unsupervised domain adaptation (UDA) which aims at adapting models trained on a labeled domain to a completely unlabeled domain by incorporating a domain mixup strategy in domain adversarial learning model by linearly interpolating between the source and target domain samples. Expand
MiCo: Mixup Co-Training for Semi-Supervised Domain Adaptation
TLDR
A new approach for SSDA is proposed, which is to explicitly decompose SSDA into two sub-problems: a semi-supervised learning problem in the target domain and an unsupervised domain adaptation (UDA) problem across domains. Expand
AFAN: Augmented Feature Alignment Network for Cross-Domain Object Detection
TLDR
This work proposes a novel augmented feature alignment network (AFAN) which integrates intermediate domain image generation and domain-adversarial training into a unified framework and significantly outperforms the state-of-the-art methods on standard benchmarks for both similar and dissimilar domain adaptations. Expand
Domain Generalization Needs Stochastic Weight Averaging for Robustness on Domain Shifts
TLDR
To estimate the center, stochastic weight averaging (SWA) is employed and theoretical analysis describing how SWA supports the generalization bound for an unseen domain and achieves state-of-theart performances over all of widely used domain generalization benchmarks. Expand
Adaptive Methods for Real-World Domain Generalization
TLDR
This work proposes a domain-adaptive approach, which uses a discriminative domain embedding from unsupervised training examples to build a domainadaptive model, that takes both the input as well as its domain into account while making predictions, and achieves state-of-the-art performance on various domain generalization benchmarks. Expand
Select, Label, and Mix: Learning Discriminative Invariant Feature Representations for Partial Domain Adaptation
TLDR
A novel 'Select, Label, and Mix' (SLM) framework that aims to learn discriminative invariant feature representations for partial domain adaptation and demonstrates the superiority of the proposed framework over state-of-the-art methods. Expand
Exploiting Domain-Specific Features to Enhance Domain Generalization
TLDR
This paper proposes 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 and empirically shows that mDSDI provides competitive results with state-of-the-art techniques in DG. Expand
Domain Generalization via Gradient Surgery
TLDR
This work characterize the conflicting gradients emerging in domain shift scenarios and devise novel gradient agreement strategies based on gradient surgery to alleviate their effect, and validate the value of the proposed agreement strategy in enhancing the generalization capability of deep learning models indomain shift scenarios. Expand
SelfReg: Self-supervised Contrastive Regularization for Domain Generalization
TLDR
A new regularization method for domain generalization based on contrastive learning, self-supervised contrastive regularization (SelfReg), which use only positive data pairs, thus it resolves various problems caused by negative pair sampling and proposes a class-specific domain perturbation layer (CDPL), which makes it possible to effectively apply mixup augmentation even when onlypositive data pairs are used. Expand
COLUMBUS: Automated Discovery of New Multi-Level Features for Domain Generalization via Knowledge Corruption
TLDR
This work proposes COLUMBUS, a method that enforces new feature discovery via a targeted corruption of the most relevant input and multi-level representations of the data that achieves new state-of-the-art results by outperforming 18 DG algorithms on multiple DG benchmark datasets in the DOMAINBED framework. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 18 REFERENCES
A DIRT-T Approach to Unsupervised Domain Adaptation
TLDR
Two novel and related models are proposed: the Virtual Adversarial Domain Adaptation (VADA) model, which combines domain adversarial training with a penalty term that punishes the violation the cluster assumption, and the Decision-boundary Iterative Refinement Training with a Teacher (DIRT-T) models, which takes the VADA model as initialization and employs natural gradient steps to further minimize the Cluster assumption violation. Expand
Adversarial Discriminative Domain Adaptation
TLDR
It is shown that ADDA is more effective yet considerably simpler than competing domain-adversarial methods, and the promise of the approach is demonstrated by exceeding state-of-the-art unsupervised adaptation results on standard domain adaptation tasks as well as a difficult cross-modality object classification task. Expand
Domain-Adversarial Training of Neural Networks
TLDR
A new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions, which can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. Expand
Conditional Adversarial Domain Adaptation
TLDR
Conditional adversarial domain adaptation is presented, a principled framework that conditions the adversarial adaptation models on discriminative information conveyed in the classifier predictions to guarantee the transferability. Expand
CyCADA: Cycle-Consistent Adversarial Domain Adaptation
TLDR
A novel discriminatively-trained Cycle-Consistent Adversarial Domain Adaptation model that adapts representations at both the pixel-level and feature-level, enforces cycle-consistency while leveraging a task loss, and does not require aligned pairs is proposed. Expand
Joint Domain Alignment and Discriminative Feature Learning for Unsupervised Deep Domain Adaptation
TLDR
Joint domain alignment and discriminative feature learning is proposed, both of which guarantee the domain invariant features with better intra-class compactness and inter-class separability. Expand
Learning Transferable Features with Deep Adaptation Networks
TLDR
A new Deep Adaptation Network (DAN) architecture is proposed, which generalizes deep convolutional neural network to the domain adaptation scenario and can learn transferable features with statistical guarantees, and can scale linearly by unbiased estimate of kernel embedding. Expand
Self-ensembling for visual domain adaptation
TLDR
In small image benchmarks, the use of self-ensembling for visual domain adaptation problems not only outperforms prior art, but can also achieve accuracy that is close to that of a classifier trained in a supervised fashion. Expand
Asymmetric Tri-training for Unsupervised Domain Adaptation
TLDR
This work proposes the use of an asymmetric tri-training method for unsupervised domain adaptation, where two networks are used to label unlabeled target samples, and one network is trained by the pseudo-labeled samples to obtain target-discriminative representations. Expand
mixup: Beyond Empirical Risk Minimization
TLDR
This work proposes mixup, a simple learning principle that trains a neural network on convex combinations of pairs of examples and their labels, which improves the generalization of state-of-the-art neural network architectures. Expand
...
1
2
...