Multi-Adversarial Domain Adaptation

Pei, Zhongyi; Cao, Zhangjie; Long, Mingsheng; Wang, Jianmin

doi:10.48550/arxiv.1809.02176

Cited by 20 publications

(25 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We extend domain adversarial neural network (DANN) [7], conditional adversarial domain adaptation (CDAN) [16] with the proposed category-invariant feature enhancement (CIFE). We compare with a number of state-of-theart methods: Deep adaptation network (DAN) [15], domain adversarial neural network (DANN) [7], joint adaptation network (JAN) [17], multi-adversarial domain adaptation (MADA) [19], conditional adversarial domain adaptation (CDAN) [16], adversarial discriminative domain adaptation (ADDA) [23], cycle-consistent adversarial domain adaptation (CyCADA) [12], batch spectral penalization (BSP) [4], dynamic adversarial domain adaptation (DAAN) [30], batch nuclear-norm maximization (BNM) [5], enhanced transport distance (ETD) [14] and label propagation with augmented anchors (A 2 LP) [31].…”

Section: Comparison Methodsmentioning

confidence: 99%

“…The adversarial discriminative domain adaptation (ADDA) uses asymmetric feature extractors for the two domains to conduct the alignment [23]. The multiadversarial domain adaptation (MADA) captures multimode structures by re-weighting features with category predictions [19]. The cycle-consistent adversarial domain adaptation (CyCADA) implements domain adaptation at both pixel-level and feature-level by using cycle-consistent adversarial training [12].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

Wu¹,

Inkpen²,

El-Roby³

2021

Preprint

View full text Add to dashboard Cite

Adversarial domain adaptation has made impressive advances in transferring knowledge from the source domain to the target domain by aligning feature distributions of both domains. These methods focus on minimizing domain divergence and regard the adaptability, which is measured as the expected error of the ideal joint hypothesis on these two domains, as a small constant. However, these approaches still face two issues: (1) Adversarial domain alignment distorts the original feature distributions, deteriorating the adaptability; (2) Transforming feature representations to be domain-invariant needs to sacrifice domain-specific variations, resulting in weaker discriminability. In order to alleviate these issues, we propose category-invariant feature enhancement (CIFE), a general mechanism that enhances the adversarial domain adaptation through optimizing the adaptability. Specifically, the CIFE approach introduces category-invariant features to boost the discriminability of domain-invariant features with preserving the transferability. Experiments show that the CIFE could improve upon representative adversarial domain adaptation methods to yield state-of-the-art results on five benchmarks.

show abstract

Section: Comparison Methodsmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

Wu¹,

Inkpen²,

El-Roby³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Specifically, the domain-adversarial neural network (DANN) [17] first leverages adversarial learning between the domain classifier and feature generator to learn domain-invariant representations by adding a simple gradient reversal layer (GRL). Further, to address the mode collapse issue, multi-adversarial domain adaptation (MADA) [30] presents a multi-adversarial domain adaptation approach with the help of multiple domain classifiers. The adversarial discriminative domain adaptation (ADDA) [18] uses label learning in the source domain to distinguish representations, and then uses asymmetric mapping (without weight sharing) learned by standard generative adversarial network (GAN) loss to map the target data onto a separate code in the same space.…”

Section: Unsupervised Domain Adversarial Adaptationmentioning

confidence: 99%

“…Designed in cycle-consistent adversarial domain adaptation (CyCADA) [31], cyclic consistency loss strengthens the consistency of structure and semantics during adversarial domain adaptation (ADA). MADA [30] captures multi-modal structures to achieve fine-grained alignment of different data distributions based on multiple domain identifiers. Co-regularized domain alignment (Co-DA) [32] constructs a number of different feature spaces, and aligns the source and target distributions in each feature space.…”

Section: Unsupervised Domain Adversarial Adaptationmentioning

confidence: 99%

“…According to the adversarial-based domain adaption, the distribution shift between the source and the target domains is reduced by generating globally transferable features [17,30]. The existing adversarial strategy can be regarded as a two-player game, where the first player is the domain discriminator D, who distinguishes the source domain from the target domain, and the second player is the feature generator G simultaneously trained to confuse the discrimination results of D. To obtain domain-invariant features F, the trainable parameters θ g , θ d and θ c are optimized by minimizing the losses of the three modules G, D and C alternately.…”

Section: The Training Based On Triple Adversarial Strategymentioning

confidence: 99%

See 1 more Smart Citation

A Triple Adversary Network Driven by Hybrid High-Order Attention for Domain Adaptation

Wang¹,

Fu²

2020

Electronics

View full text Add to dashboard Cite

How to bridge the knowledge gap between the annotated source domain and the unlabeled target domain is a basic challenge to domain adaptation. The existing approaches can relieve this gap by feature alignments across domains; however, aligning non-transferable features may lead to negative shift confusing the knowledge learning on target domains. In this paper, a triple adversary network is proposed on the basis of a high-order attention, hopefully to solve the problem. The proposed architecture focuses on the detailed feature alignment by a hybrid high-order attention using a fast iteration algorithm. In addition, an orthogonal loss of two complementary modules is applied to constrain the mutual exclusion of foreground and background features. Finally, a triple adversarial strategy is introduced to further improve the training convergence for the composed architectures. Numeric experiments on datasets of Digits, Office-31 and Office-home illuminate that the proposed network can effectively improve the state-of-art domain adaptations with superior transferring performance.

show abstract

Cross-Domain Error Minimization for Unsupervised Domain Adaptation

Chen

Cui

et al. 2021

Database Systems for Advanced Applications

View full text Add to dashboard Cite

Unsupervised domain adaptation aims to transfer knowledge from a labeled source domain to an unlabeled target domain. Previous methods focus on learning domain-invariant features to decrease the discrepancy between the feature distributions as well as minimizing the source error and have made remarkable progress. However, a recently proposed theory reveals that such a strategy is not sufficient for a successful domain adaptation. It shows that besides a small source error, both the discrepancy between the feature distributions and the discrepancy between the labeling functions should be small across domains. The discrepancy between the labeling functions is essentially the cross-domain errors which are ignored by existing methods. To overcome this issue, in this paper, a novel method is proposed to integrate all the objectives into a unified optimization framework. Moreover, the incorrect pseudo labels widely used in previous methods can lead to error accumulation during learning. To alleviate this problem, the pseudo labels are obtained by utilizing structural information of the target domain besides source classifier and we propose a curriculum learning based strategy to select the target samples with more accurate pseudo-labels during training. Comprehensive experiments are conducted, and the results validate that our approach outperforms state-of-the-art methods.

show abstract

Multi-Adversarial Domain Adaptation

Cited by 20 publications

References 14 publications

Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

Towards Category and Domain Alignment: Category-Invariant Feature Enhancement for Adversarial Domain Adaptation

A Triple Adversary Network Driven by Hybrid High-Order Attention for Domain Adaptation

Cross-Domain Error Minimization for Unsupervised Domain Adaptation

Contact Info

Product

Resources

About