Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

Wang, Qian; Breckon, Toby P.

doi:10.1609/aaai.v34i04.6091

Cited by 183 publications

(150 citation statements)

References 19 publications

Supporting

Mentioning

150

Contrasting

Order By: Relevance

“…MASF [Pattern Recognit.2020] employs an L2 constraint combining sparse filtering to learn both domain-shared and discriminative representations. Selective pseudo-labeling (SPL): [ 36 ]. SPL [AAAI2020] is also a selective pseudo labeling strategy based on structured prediction.…”

Section: Methodsmentioning

confidence: 99%

“…Selective pseudo-labeling (SPL): [ 36 ]. SPL [AAAI2020] is also a selective pseudo labeling strategy based on structured prediction.…”

Section: Methodsmentioning

confidence: 99%

“…Following the setting of [ 35 , 36 ], we report the classification accuracy on target data as the evaluation metric.

where

denotes the predicted label and y is the true label, so

.…”

Section: Methodsmentioning

confidence: 99%

See 2 more Smart Citations

Discriminative Sparse Filtering for Multi-Source Image Classification

Han

Zhou

Yang

et al. 2020

Sensors

View full text Add to dashboard Cite

Distribution mismatch caused by various resolutions, backgrounds, etc. can be easily found in multi-sensor systems. Domain adaptation attempts to reduce such domain discrepancy by means of different measurements, e.g., maximum mean discrepancy (MMD). Despite their success, such methods often fail to guarantee the separability of learned representation. To tackle this issue, we put forward a novel approach to jointly learn both domain-shared and discriminative representations. Specifically, we model the feature discrimination explicitly for two domains. Alternating discriminant optimization is proposed to obtain discriminative features with an l2 constraint in labeled source domain and sparse filtering is introduced to capture the intrinsic structures exists in the unlabeled target domain. Finally, they are integrated in a unified framework along with MMD to align domains. Extensive experiments compared with state-of-the-art methods verify the effectiveness of our method on cross-domain tasks.

show abstract

Section: Methodsmentioning

confidence: 99%

“…Selective pseudo-labeling (SPL): [ 36 ]. SPL [AAAI2020] is also a selective pseudo labeling strategy based on structured prediction.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

Discriminative Sparse Filtering for Multi-Source Image Classification

Han

Zhou

Yang

et al. 2020

Sensors

View full text Add to dashboard Cite

show abstract

“…The high dimensional feature space always contain noise information or redundant information. To address this, we adopt PCA to reduce the dimension of the feature first and obtain more robust feature compared with original feature data as in [Wang and Breckon, 2019]. We concatenated the features from the visual representation of 2D images and 3D objects as a matrix…”

Section: Subspace Generationmentioning

confidence: 99%

“…We first initialize the cluster center of the target domain by Eq.(4). Then, to make the cluster centroid of the target domain close to the class prototype of the source domain, we define the optimization problem as in [Wang and Breckon, 2019]:…”

Section: Intrinsic Structure Of the Source Domainmentioning

confidence: 99%

Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval

Song

et al. 2020

Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence

View full text Add to dashboard Cite

2D image-based 3D objects retrieval is a new topic for 3D objects retrieval which can be used to manage 3D data with 2D images. The goal is to search some related 3D objects when given a 2D image. The task is challenging due to the large domain gap between 2D images and 3D objects. Therefore, it is essential to consider domain adaptation problems to reduce domain discrepancy. However, most of the existing domain adaptation methods only utilize the semantic information from the source domain to predict labels in the target domain and neglect the intrinsic structure of the target domain. In this paper, we propose a domain alignment framework with consistent domain structure learning to reduce the large gap between 2D images and 3D objects. The domain structure learning module makes use of both the semantic information from the source domain and the intrinsic structure of the target domain, which provides more reliable predicted labels to the domain alignment module to better align the conditional distribution. We conducted experiments on two public datasets, MI3DOR and MI3DOR-2, and the experimental results demonstrate the proposed method outperforms the state-of-the-art methods.

show abstract

Domain adaptation via incremental confidence samples into classification

Teng

Zheng

et al. 2021

Int J Intell Syst

View full text Add to dashboard Cite

To accurately recognize similar objects in different domains, the key for domain adaptation is to learn new metrics so as to minimize the discrepancy of two domains. Recent works utilize joint probability domain adaptation to tackle this problem but get poor performance due to poor discriminability or transferability of data sets. The inaccurate pseudo‐labeling in the feature subspace can lead to a chain reaction of errors during iterations, and varieties of the joint probability distribution values further aggravate the miscalculation. To cope with the above problems, this paper proposes a unified framework by introducing Incremental Confidence Samples into Classification (ICSC). ICSC includes both incrementally labeling and adaptively adjusting. With the increase of confidence samples in each iteration, incrementally labeling is used to reduce error accumulations and progressively guarantee good classification performance effectively. Moreover, the tradeoff weight between within‐class and between‐class distance is adaptively adjusted according to the importance of transferability and discriminability. Consequently, the discrepancy minimization of within‐class and the discrepancy maximization of between‐class are achieved. Extensive experiments on several benchmark data sets demonstrate the effectiveness of the proposed method over the state‐of‐the‐art methods.

show abstract

Unsupervised Domain Adaptation via Structured Prediction Based Selective Pseudo-Labeling

Cited by 183 publications

References 19 publications

Discriminative Sparse Filtering for Multi-Source Image Classification

Discriminative Sparse Filtering for Multi-Source Image Classification

Consistent Domain Structure Learning and Domain Alignment for 2D Image-Based 3D Objects Retrieval

Domain adaptation via incremental confidence samples into classification

Contact Info

Product

Resources

About