Active Adversarial Domain Adaptation

@article{Su2020ActiveAD,
  title={Active Adversarial Domain Adaptation},
  author={Jong-Chyi Su and Yi-Hsuan Tsai and Kihyuk Sohn and Buyu Liu and Subhransu Maji and Manmohan Chandraker},
  journal={2020 IEEE Winter Conference on Applications of Computer Vision (WACV)},
  year={2020},
  pages={728-737}
}
We propose an active learning approach for transferring representations across domains. Our approach, active adversarial domain adaptation (AADA), explores a duality between two related problems: adversarial domain alignment and importance sampling for adapting models across domains. The former uses a domain discriminative model to align domains, while the latter utilizes the model to weigh samples to account for distribution shifts. Specifically, our importance weight promotes unlabeled… Expand
Stochastic Adversarial Gradient Embedding for Active Domain Adaptation
TLDR
This paper introduces \textit{Stochastic Adversarial Gradient Embedding} (SAGE), a framework that makes a triple contribution to ADA and demonstrates that SAGE takes the best of uncertainty and diversity samplings and improves representations transferability substantially. Expand
Discriminative Active Learning for Domain Adaptation
TLDR
This work proposes a discriminative active learning approach for domain adaptation to reduce the efforts of data annotation and proposes three-stage active adversarial training of neural networks: invariant feature space learning, uncertainty and diversity criteria and their trade-off for query strategy and re-training with queried target labels. Expand
Active Universal Domain Adaptation
Most unsupervised domain adaptation methods rely on rich prior knowledge about the source-target label set relationship, and they cannot recognize categories beyond the source classes, which limitsExpand
Adaptation Across Extreme Variations using Unlabeled Bridges
TLDR
This work proposes to decompose domain discrepancy into multiple but smaller, and thus easier to minimize, discrepancies by introducing unlabeled bridging domains that connect the source and target domains. Expand
S3VAADA: Submodular Subset Selection for Virtual Adversarial Active Domain Adaptation
TLDR
This work proposes SVAADA which introduces a novel submodular criterion to select a maximally informative subset to label and enhances a cluster-based DA procedure through novel improvements to effectively utilize all the available data for improving generalization on target. Expand
Dynamic Weighted Learning for Unsupervised Domain Adaptation
  • Ning Xiao, Lei Zhang
  • Computer Science
  • 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2021
TLDR
Dynamic Weighted Learning is proposed to avoid the discriminability vanishing problem caused by excessive alignment learning and domain misalignment problem causedby excessive discriminant learning and has an excellent performance in several benchmark datasets. Expand
Improving Semi-Supervised Domain Adaptation Using Effective Target Selection and Semantics
TLDR
It is shown that initializing the class-representations or prototypes with theclass-semantics helps in bridging the domain gap significantly, along with adversarially learnt entropy objective results in a novel framework, termed STar (Select TARgets), which sets a new state-of-the-art for the SSDA task. Expand
Transferable Query Selection for Active Domain Adaptation
Unsupervised domain adaptation (UDA) enables transferring knowledge from a related source domain to a fully unlabeled target domain. Despite the significant advances in UDA, the performance gapExpand
Unsupervised Domain Alignment to Mitigate Low Level Dataset Biases
TLDR
This paper proposes a novel debiasing technique to reduce the effects of a biased training dataset by learning a non-linear mapping from the source domain (training set) to the target domain (testing set) while retaining training set labels. Expand
Multi-Anchor Active Domain Adaptation for Semantic Segmentation
TLDR
A novel multi-anchor based active learning strategy is introduced to assist domain adaptation regarding the semantic segmentation task by regularizing the latent representation of the target samples compact around multiple anchors through a novel soft alignment loss, more precise segmentation can be achieved. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 80 REFERENCES
Partial Adversarial Domain Adaptation
TLDR
This paper presents Partial Adversarial Domain Adaptation (PADA), which simultaneously alleviates negative transfer by down-weighing the data of outlier source classes for training both source classifier and domain adversary, and promotes positive transfer by matching the feature distributions in the shared label space. 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
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
Few-Shot Adversarial Domain Adaptation
TLDR
This work provides a framework for addressing the problem of supervised domain adaptation with deep models by carefully designing a training scheme whereby the typical binary adversarial discriminator is augmented to distinguish between four different classes. Expand
Adversarial Multiple Source Domain Adaptation
TLDR
This paper proposes multisource domain adversarial networks (MDAN) that approach domain adaptation by optimizing task-adaptive generalization bounds and conducts extensive experiments showing superior adaptation performance on both classification and regression problems: sentiment analysis, digit classification, and vehicle counting. Expand
Domain Adaptation for Structured Output via Discriminative Patch Representations
TLDR
A domain adaptation method to adapt the source data to the unlabeled target domain by discovering multiple modes of patch-wise output distribution through the construction of a clustered space and using an adversarial learning scheme to push the feature representations of target patches in the clustered space closer to the distributions of source patches. Expand
Collaborative and Adversarial Network for Unsupervised Domain Adaptation
TLDR
A new unsupervised domain adaptation approach called Collaborative and Adversarial Network (CAN) is proposed through domain-collaborative and domain-adversarial training of neural networks and extended as Incremental CAN (iCAN), in which a set of pseudo-labelled target samples are selected based on the image classifier and the last domain classifier from the previous training epoch. 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
Progressive Domain Adaptation for Object Detection
TLDR
This paper proposes to bridge the domain gap with an intermediate domain and progressively solve easier adaptation subtasks by adopting adversarial learning to align distributions at the feature level. Expand
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
TLDR
This paper introduces the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems, and outperforms baselines across different settings on multiple large-scale datasets. Expand
...
1
2
3
4
5
...