Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

Fu, Tingting; Liu, Ying

doi:10.1109/access.2021.3087867

Cited by 9 publications

(3 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To demonstrate the efficiency of our VTL, the results of our experiments are compared with several unsupervised domain adaptation methods including EMFS (2018) [40], EasyTL (2019) [41], STJML (2020) [42], GEF (2019) [43], DWDA (2021) [44], CDMA (2020) [45], ALML (2022) [46], TTLC (2021) [33], SGA-MDAP (2020) [47], NSO (2020) [48], FSUTL (2020) [49], PLC (2021) [50], GSI (2021) [51] and ICDAV (2022) [52]. In the experiments, VTL begins with learning a domain invariant and class discriminative latent feature space according to Equation (18).…”

Section: Resultsmentioning

confidence: 99%

Visual Transductive learning via Iterative Label Correction

Rezaie,

Ahmadvand,

Tahmoresnezhad

2023

Preprint

View full text Add to dashboard Cite

Unsupervised domain adaptation (UDA) aims to transfer knowledge across domains when there is no labeled data available in the target domain. In this way, UDA methods attempt to utilize pseudo-labeled target samples to align distribution across the source and target domains. To mitigate the negative impact of inaccurate pseudo-labeling on knowledge transfer, we propose a novel UDA method known as visual transductive learning via iterative label correction (VTL) that benefits from a novel label correction paradigm. Specifically, we learn a domain invariant and class discriminative latent feature representation for samples of both source and target domains. Simultaneously, VTL attempts to locally align the information of samples by learning the geometric structure of samples. In the new shared feature space, the novel label correction paradigm is utilized to effectively maximize the reliability of pseudo labels by correcting inaccurate pseudo-labeled target samples, which significantly improves VTL classification performance. The experimental results on several object recognition tasks verified our proposed VTL superiority in comparison with other state-of-the-arts.

show abstract

Section: Resultsmentioning

confidence: 99%

Visual Transductive learning via Iterative Label Correction

Rezaie,

Ahmadvand,

Tahmoresnezhad

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…But this unbiased assignment in pseudo labels easily contains noise. To relieve this issue, common solutions include combining pseudo labels from various models [6][7][8] and learning self-defined classifier function [9][10][11]. In addition, pseudo labels after biased selection participate in feature mapping learning, which is benefit to improve the effect of transfer learning.…”

Section: Introductionmentioning

confidence: 99%

Pseudo-label self-training model for transfer learning algorithm

Chen

Ling

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

When aligning joint distributions between domains, the existing transfer learning algorithms usually assign pseudo labels due to the lack of labels in target domain. However, the noise in pseudo labels will affect the performance of transfer learning. Pseudo-label self-training for transfer learning (PST-TL) model is proposed to generate reliable pseudo labels for target domain and have a wide range of applications in existing algorithms. Pseudo labels are predicted by an ensemble classifier using absolute majority vote, and labels predicted successfully are considered to be high confidence. The training of ensemble classifier applies the self-training of joint pseudo labels strategy, adding strongly stable data to training set of the classifier. The semi-supervised and unsupervised transfer learning tasks in experiment show that the existing transfer learning algorithm can significantly improve the transfer performance after embedded by PST-TL model.

show abstract

“…Unsupervised Domain Adaptation based on Pseudo-Label Confidence (UDA-PLC) [27] by projecting data of source and target domains into a latent subspace aligns the distribution of data in two domains and improves the discriminability of features in both domains. Then, UDA-PLC applies Structured Prediction (SP) and Nearest Class Prototype (NCP) to predict pseudo-labels of data in the target domain, and it performs sample selection in every iteration.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised Domain Adaptation for Image Classification Using Non-Euclidean Triplet Loss

Sarhan

Balafar²,

Feizi‐Derakhshi³

2022

Electronics

View full text Add to dashboard Cite

In recent years, computer vision tasks have increasingly used deep learning techniques. In some tasks, however, due to insufficient data, the model is not properly trained, leading to a decrease in generalizability. When trained on a dataset and tested on another similar dataset, the model predicts near-random results. This paper presents an unsupervised multi-source domain adaptation that improves transfer learning and increases generalizability. In the proposed method, a new module infers the source of the input data based on its extracted features. By making the features extractor compete against this objective, the learned feature representation generalizes better across the sources. As a result, representations similar to those from different sources are learned. That is, the extracted representation is generic and independent of any particular domain. In the training stage, a non-Euclidean triplet loss function is also utilized. Similar representations for samples belonging to the same class can be learned more effectively using the proposed loss function. We demonstrate how the developed framework may be applied to enhance accuracy and outperform the outcomes of already effective transfer learning methodologies. We demonstrate how the proposed strategy performs particularly well when dealing with various dataset domains or when there are insufficient data.

show abstract

Unsupervised Domain Adaptation Based on Pseudo-Label Confidence

Cited by 9 publications

References 32 publications

Visual Transductive learning via Iterative Label Correction

Visual Transductive learning via Iterative Label Correction

Pseudo-label self-training model for transfer learning algorithm

Unsupervised Domain Adaptation for Image Classification Using Non-Euclidean Triplet Loss

Contact Info

Product

Resources

About