Unsupervised Domain Adaptation Through Dynamically Aligning Both the Feature and Label Spaces

Qiu, Tian; Zhu, Yanan; Sun, Heyang; Chen, Songcan; Yin, Hujun

doi:10.1109/tcsvt.2022.3192135

Cited by 34 publications

(5 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We compare GPTKL with some state-of-the-art UDA methods, including DAN [9], DANN [10], CDAN [12], MCD [27], BSP based on CDAN (BSP+CDAN) [19], SAFN [28], ETD [29], GPDA [36], Challenging Tough Samples (CTSN) [46], DWL [20], DSAN [25], DAFL [21], DMP [30] and DCAN [13]. The results of baselines are cited from their original papers or were generated on our platform with the released source codes of original papers.…”

Section: Experiments Resultsmentioning

confidence: 99%

“…To solve this problem, Dynamic Weighted Learning (DWL) [20] introduces a dynamic weight to adjust the importance of domain alignment loss and discrimination learning loss in real time. Similarly, Dynamically Aligning both the Feature and Label (DAFL) [21] introduces a dynamic balancing weight in adversarial training to balance the generating and discrimination abilities of the model. However, updating dynamic weights in real time introduces additional calculations and takes more training time.…”

Section: Deep Uda Methodsmentioning

confidence: 99%

“…As shown in Figure 1c, excessive discrimination learning leads to feature misalignment between source and target domains. Some recent research works [20,21] have introduced a dynamic weight to balance discrimination learning and alignment learning in real time. However, updating dynamic weights in real time introduces additional calculations and takes more training time.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Ge,

Sun

2023

Mathematics

View full text Add to dashboard Cite

The discriminability and transferability of models are two important factors for the success of domain adaptation methods. Recently, some domain adaptation methods have improved models by adding a discriminant information extraction module. However, these methods need to carefully balance the discriminability and transferability of a model. To address this problem, we propose a new deep domain adaptation method, Gaussian Process-based Transfer Kernel Learning (GPTKL), which can perform domain knowledge transfer and improve the discrimination ability of the model simultaneously. GPTKL uses the kernel similarity between all samples in the source and target domains as a priori information to establish a cross-domain Gaussian process. By maximizing its likelihood function, GPTKL reduces the domain discrepancy between the source and target domains, thereby enhancing generalization across domains. At the same time, GPTKL introduces the deep kernel learning strategy into the cross-domain Gaussian process to learn a transfer kernel function based on deep features. Through transfer kernel learning, GPTKL learns a deep feature space with both discriminability and transferability. In addition, GPTKL uses cross-entropy and mutual information to learn a classification model shared by the source and target domains. Experiments on four benchmarks show that GPTKL achieves superior classification performance over state-of-the-art methods.

show abstract

Section: Experiments Resultsmentioning

confidence: 99%

Section: Deep Uda Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Ge,

Sun

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Unsupervised Domain adaptation(UDA). Domain adaptation seeks to transfer information from labeled source domain to unlabeled o target domain [2], [21]- [24]. The existing UDA methods can be roughly divided into two categories, one is based on distribution alignment, and another is based on semisupervised learning.…”

Section: Related Workmentioning

confidence: 99%

Adaptive Mutual Learning for Unsupervised Domain Adaptation

Zhou

Xiao

et al. 2023

IEEE Trans. Circuits Syst. Video Technol.

View full text Add to dashboard Cite

Unsupervised domain adaptation aims to transfer knowledge from labeled source domain to unlabeled target domain. The semi-supervised method based on mean-teacher framework is one of the main stream approaches. By enforcing consistency constraints, it is hopeful that the teacher network will distill useful source domain knowledge to the student network. However, in practice negative transfer often emerges because the performance of the teacher network is not guaranteed to be always better than the student network. To address this limitation, a novel Adaptive Mutual Learning (AML) strategy is proposed in this paper. Specifically, given a target sample, the network with worse prediction will be optimized by pushing its prediction close to the better prediction. This is in the spirit of traditional knowledge distillation. On the other hand, the network with better prediction is further refined by requiring its prediction to stay away from the worse prediction. This can be regarded conceptually as reverse knowledge distillation. In this way, two networks learn from each other according to their respective performance. At inference phase, the averaged output of these two networks can be taken as the final prediction. Experimental results demonstrate that our AML achieves competitive results.

show abstract

“…The model can better learn shared features and category structures between the source and target domains, thereby enhancing its generalization ability in multi-class problems. This class-level distance-based domain alignment method can achieve better performance in more complex real-world scenarios and provides an effective solution for cross-domain classification tasks [24][25][26][27][28][29]. Chen et al proposed a multi-kernel domain adaptive network for fault diagnosis in WT systems.…”

Section: Introductionmentioning

confidence: 99%

Dynamic Condition Adversarial Adaptation for Fault Diagnosis of Wind Turbine Gearbox

Zhang,

Wang,

Zhang

et al. 2023

Sensors

View full text Add to dashboard Cite

While deep learning has found widespread utility in gearbox fault diagnosis, its direct application to wind turbine gearboxes encounters significant hurdles. Disparities in data distribution across a spectrum of operating conditions for wind turbines result in a marked decrease in diagnostic accuracy. In response, this study introduces a tailored dynamic conditional adversarial domain adaptation model for fault diagnosis in wind turbine gearboxes amidst cross-condition scenarios. The model adeptly adjusts the importance of aligning marginal and conditional distributions using distance metric factors. Information entropy parameters are also incorporated to assess individual sample transferability, prioritizing highly transferable samples during domain alignment. The amalgamation of these dynamic factors empowers the approach to maintain stability across varied data distributions. Comprehensive experiments on both gear and bearing data validate the method’s efficacy in cross-condition fault diagnosis. Comparative outcomes demonstrate that, when contrasted with four advanced transfer learning techniques, the dynamic conditional adversarial domain adaptation model attains superior accuracy and stability in multi-transfer tasks, making it notably suitable for diagnosing wind turbine gearbox faults.

show abstract

Unsupervised Domain Adaptation Through Dynamically Aligning Both the Feature and Label Spaces

Cited by 34 publications

References 50 publications

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Gaussian Process-Based Transfer Kernel Learning for Unsupervised Domain Adaptation

Adaptive Mutual Learning for Unsupervised Domain Adaptation

Dynamic Condition Adversarial Adaptation for Fault Diagnosis of Wind Turbine Gearbox

Contact Info

Product

Resources

About