Adversarial transfer learning for cross-domain visual recognition

Wang, Shanshan; Zhang, Lei; Fu, Jingru

doi:10.1016/j.knosys.2020.106258

Cited by 13 publications

(5 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Transfer learning, whose core is to achieve the purpose of assisting the learning process in the target domain by finding the similarity between the source domain and target domain, has shown great effectiveness in many fields [54][55][56]. Transfer learning provides a fruitful approach for learning from existing knowledge in the original domain, applying it to new domain based on the similarity of the datasets.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Mixed Multi-Pattern Regression for DNI Prediction in Arid Desert Areas

Han,

Wang,

Wang

et al. 2023

Sustainability

View full text Add to dashboard Cite

As a crucial issue in renewable energy, accurate prediction of direct normal solar irradiance (DNI) is essential for the stable operation of concentrated solar power (CSP) stations, especially for those in arid desert areas. In this study, in order to fully explore the laws of climate change and assess the solar resources in arid desert areas, we have proposed a mixed multi-pattern regression model (MMP) for short-term DNI prediction using prior knowledge provided by the clear-sky solar irradiance (CSI) model and time series patterns of key meteorological factors mined using PR-DTW on different time scales. The contrastive experimental results demonstrated that MMP can outperform existing DNI prediction models in terms of three recognized statistical metrics. To address the challenge of limited data in arid desert areas, we presented the T-MMP model involving combined transfer learning and MMP. The experimental results demonstrated that T-MMP outperformed MMP in DNI prediction by exploiting the significant correlation between meteorological time series patterns in similar areas for data augmentation. Our study provided a valuable prediction model for accurate DNI prediction in arid desert areas, facilitating the economical and stable operation of CSP plants.

show abstract

Section: Discussionmentioning

confidence: 99%

“…domain, has shown great effectiveness in many fields [54][55][56]. Transfer learning provides a fruitful approach for learning from existing knowledge in the original domain, applying it to new domain based on the similarity of the datasets.…”

Section: Discussionmentioning

confidence: 99%

Mixed Multi-Pattern Regression for DNI Prediction in Arid Desert Areas

Han,

Wang,

Wang

et al. 2023

Sustainability

View full text Add to dashboard Cite

show abstract

“…Deepharmony (Dewey et al 2019) uses paired data to change the contrast of MRI from one scanner to another scanner with a modified U-Net. Generative Adversarial Networks (Huang et al 2018;Sankaranarayanan et al 2018;Lei et al 2019;Wang, Zhang, and Fu 2020) aim to generate new images to overcome the domain shift. Those methods modify the intensities of each pixel before training for the main task.…”

Section: Related Workmentioning

confidence: 99%

Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis

Wolleb¹,

Sandkühler²,

Bieder³

et al. 2021

Preprint

View full text Add to dashboard Cite

Limited availability of large image datasets is a major issue in the development of accurate and generalizable machine learning methods in medicine. The limitations in the amount of data are mainly due to the use of different acquisition protocols, different hardware, and data privacy. At the same time, training a classification model on a small dataset leads to a poor generalization quality of the model. To overcome this issue, a combination of various image datasets of different provenance is often used, e.g., multi-site studies. However, if an additional dataset does not include all classes of the task, the learning of the classification model can be biased to the device or place of acquisition. This is especially the case for Magnetic Resonance (MR) images, where different MR scanners introduce a bias that limits the performance of the model. In this paper, we present a novel method that learns to ignore the scanner-related features present in the images, while learning features relevant for the classification task. We focus on a real-world scenario, where only a small dataset provides images of all classes. We exploit this circumstance by introducing specific additional constraints on the latent space, which lead the focus on disease-related rather than scannerspecific features. Our method Learn to Ignore outperforms state-of-the-art domain adaptation methods on a multi-site MRI dataset on a classification task between Multiple Sclerosis patients and healthy subjects.

show abstract

“…The main difficulties of this task are that machine learning technology is primarily adopted for the recognition of massive numbers of words, but the "cold environment" (lack of a learning corpus) of poetry makes it difficult to begin the learning task. To this end, transfer learning has emerged (Wang, Zhang, & Fu, 2020), which aims to migrate labeled data or knowledge structures from relevant domains to complete the learning task in the target domain; a typical example of this is Google's BERT model (Devlin, Chang, Lee, & Toutanova, 2018). Based on it, the BERT-BiLSTM-CRFs model has been effectively used in solving large-scale entity recognition in recent years (Song, Tian, & Yu, 2020).…”

Section: Introductionmentioning

confidence: 99%

Recognition and Analysis of Emotional Words in Ancient Chinese Poetry under Different Themes

Wei

Wang

2021

Proceedings of the Association for Information Science and Tech

View full text Add to dashboard Cite

The emotional connotation in ancient poetry is a valuable human spiritual culture, adopting the key semantic technique to parse the emotional word in poetry under different themes is beneficial to discover the relationship between poetry theme and emotion. In a "cold environment" (without learning corpus) of Tang poetry, this work presents, for the first time, the automatic recognition and analysis of large-scale humanistic emotional words within ancient Chinese poetry from different themes. A "cold start" automatic citation method for character sequences is proposed to obtain the learning corpus. The best F1 and F1_distinct of trained BERT-BiLSTM-CRFs model respectively reach 96.27% and 86.04%. Deep learning expanded imagery words that convey emotion to realize knowledge discovery. The relationships between theme and emotion word show that Chinese poetry is good at using natural objects to express various sentiments to people, with each theme of poetry owns distinguished emotion feature.

show abstract

Adversarial transfer learning for cross-domain visual recognition

Cited by 13 publications

References 35 publications

Mixed Multi-Pattern Regression for DNI Prediction in Arid Desert Areas

Mixed Multi-Pattern Regression for DNI Prediction in Arid Desert Areas

Learn to Ignore: Domain Adaptation for Multi-Site MRI Analysis

Recognition and Analysis of Emotional Words in Ancient Chinese Poetry under Different Themes

Contact Info

Product

Resources

About