A Concise Review of Transfer Learning

Farahani, Abolfazl; Pourshojae, Behrouz; Rasheed, Khaled; Arabnia, Hamid R.

doi:10.1109/csci51800.2020.00065

Cited by 44 publications

(26 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning [34,36,47,48], as one of the important research branches of machine learning, helps target tasks to learn a high-quality model with the knowledge from source domains which have rich labeled data/samples but different distributions with target domains. Domain adaptation [36] is a hot topic in transfer learning and aims to adjust the distribution between domains in order to eliminate domain shift.…”

Section: Domain Adaptationmentioning

confidence: 99%

Discriminative Extreme Learning Machine with Cross‐Domain Mean Approximation for Unsupervised Domain Adaptation

Zang

et al. 2022

Complexity

View full text Add to dashboard Cite

Extreme Learning Machine (ELM) is widely used in various fields because of its fast training and high accuracy. However, it does not primarily work well for Domain Adaptation (DA) in which there are many annotated data from auxiliary domain and few even no annotated data in target domain. In this paper, we propose a new variant of ELM called Discriminative Extreme Learning Machine with Cross-Domain Mean Approximation (DELM-CDMA) for unsupervised domain adaptation. It introduces Cross-Domain Mean Approximation (CDMA) into the hidden layer of ELM to reduce distribution discrepancy between domains for domain bias elimination, which is conducive to train a high accuracy ELM on annotated data from auxiliary domains for target tasks. Linear Discriminative Analysis (LDA) is also adopted to improve the discrimination of learned model and obtain higher accuracy. Moreover, we further provide a Discriminative Kernel Extreme Learning Machine with Cross-Domain Mean Approximation (DKELM-CDMA) as the kernelization extension of DELM-CDMA. Some experiments are performed to investigate the proposed approach, and the result shows that DELM-CDMA and DKELM-CDMA could effectively extend ELM suitable for domain adaptation and outperform ELM and many other domain adaptation approaches.

show abstract

Section: Domain Adaptationmentioning

confidence: 99%

Discriminative Extreme Learning Machine with Cross‐Domain Mean Approximation for Unsupervised Domain Adaptation

Zang

et al. 2022

Complexity

View full text Add to dashboard Cite

show abstract

“…The feature-based TL emphasizes effective feature analysis like feature selection, mapping, and encoding. This type of TL method generally includes symmetric and asymmetric feature transformation [24] . The former aims to find valuable features across domains, and the latter reduces the domain difference by transforming the features of the source domain into the target domain.…”

Section: Related Workmentioning

confidence: 99%

“…This type of method aims to find these same model parameters or prior distributions to achieve knowledge transformation [26] . For example, the single-model knowledge transfer learns both the knowledge of the target domain and the transfer knowledge in the parameters of the pre-trained model to achieve the prediction task of the target domain [24] . Relation-based TL assumes that if two domains are similar, they will share a similar relationship.…”

Section: Related Workmentioning

confidence: 99%

Ambient air pollutants concentration prediction during the COVID-19: A method based on transfer learning

Chen¹,

Xu²,

Wang³

et al. 2022

Knowledge-Based Systems

View full text Add to dashboard Cite

“…19 The symmetric feature-based transfer learning approach discovers potentially meaningful structures between domains to find a common latent feature space that has predictive qualities while reducing the marginal distribution between the domains. 20 Zhang et al proposed a method to diagnose susceptibility to alcoholism by extracting features using deep learning algorithms combined with transfer learning. 21 Despite it being a popular topic, to the best of the authors' knowledge, there is no research on applying transfer learning to NIR based on nutrient-deficient pear leaf samples.…”

Section: Introductionmentioning

confidence: 99%

A Novel Tran_NAS Method for the Identification of Fe- and Mg-Deficient Pear Leaves from N- and P-Deficient Pear Leaf Data

Jin

Wang

et al. 2022

ACS Omega

View full text Add to dashboard Cite

Trace element deficiency diagnosis plays a critical role in pear cultivation. However, high-quality diagnostic models are challenging to investigate, making it difficult to collect samples. Therefore, this manuscript developed a novel transfer learning method, named Tran_NAS, with a finetuning neural network that uses a neural architecture search (NAS) to transfer learning from nitrogen (N) and phosphorus (P) to iron (Fe) and magnesium (Mg) to diagnose pear leaf element deficiencies. The best accuracy of the transferred NAS model is 89.12%, which is 11% more than that of the model without the transfer of trace element-deficient samples. Meanwhile, Tran_NAS also has better performance on source datasets after comparing with different proportions of training sets. Finally, this manuscript summarizes the transfer model coincident characteristics, including the methods of batch normalization (BN) and dropout layers, which make the model more generalizable. This manuscript applies a symmetric homogeneous feature-based transfer learning method on NAS that is designed explicitly for near-infrared (NIR) data collected from nutrient-deficient pear leaves. The novel transfer learning method would be more effective for the micro-NIR spectrum of the nondestructive diagnosis.

show abstract

A Concise Review of Transfer Learning

Cited by 44 publications

References 31 publications

Discriminative Extreme Learning Machine with Cross‐Domain Mean Approximation for Unsupervised Domain Adaptation

Discriminative Extreme Learning Machine with Cross‐Domain Mean Approximation for Unsupervised Domain Adaptation

Ambient air pollutants concentration prediction during the COVID-19: A method based on transfer learning

A Novel Tran_NAS Method for the Identification of Fe- and Mg-Deficient Pear Leaves from N- and P-Deficient Pear Leaf Data

Contact Info

Product

Resources

About