Zobrazeno 1 - 10
of 17 299
pro vyhledávání: '"Domain Adaptation"'
While speech emotion recognition (SER) research has made significant progress, achieving generalization across various corpora continues to pose a problem. We propose a novel domain adaptation technique that embodies a multitask framework with SER as
Externí odkaz:
http://arxiv.org/abs/2310.04703
Publikováno v:
Geo-spatial Information Science, Pp 1-15 (2024)
Hyperspectral datasets captured by airborne are one of the important data sources in the field of hyperspectral image fusion. However, the limited number of data samples often hinders the optimal performance of deep learning-based methods on these da
Externí odkaz:
https://doaj.org/article/2c261a1c2e244549a67f6543f2382f7c
Publikováno v:
Jisuanji kexue yu tansuo, Vol 18, Iss 9, Pp 2384-2394 (2024)
Existing 3D human pose estimators perform well on a single dataset but are limited by the single pose structure of the training data, resulting in insufficient generalization to cross-domain experiments. Existing methods mitigate this deficiency by i
Externí odkaz:
https://doaj.org/article/4232f6f5ba3e4bde8d503f707ee1ddc6
Publikováno v:
Jisuanji kexue yu tansuo, Vol 18, Iss 9, Pp 2436-2448 (2024)
The main purpose of unbiased cross-domain object detection is to utilize the knowledge of the source domain to the maximum extent through knowledge distillation, and reduce the cross-domain gap of the model through domain adaptation. However, the pse
Externí odkaz:
https://doaj.org/article/69cc600e7a07402fb07d35f75b26677e
Publikováno v:
Geo-spatial Information Science, Pp 1-18 (2024)
To enhance the adaptability and application capability of the cloud detection model in different remote sensing satellite domains, unsupervised domain adaptation methods are employed to improve the model’s robustness and transferability. However, c
Externí odkaz:
https://doaj.org/article/c6300786f6af4475a1884f901bd73b58
Publikováno v:
Leida xuebao, Vol 13, Iss 4, Pp 807-821 (2024)
This paper addresses the problem of high-resolution imaging of shadowed multiple-targets with limited labeled data, by proposing a transfer-learning-based method for through-the-wall radar imaging. First, a generative adversarial sub-network is devel
Externí odkaz:
https://doaj.org/article/2923ca0992504a12a86c402dcd787492
Publikováno v:
Autonomous Intelligent Systems, Vol 4, Iss 1, Pp 1-15 (2024)
Abstract Semantic segmentation is significant to realize the scene understanding of autonomous driving. Due to the lack of annotated real-world data, the technology of domain adaptation is applied so that the model is trained on the synthetic data an
Externí odkaz:
https://doaj.org/article/10873e5e01ea4ba897bfd17e51b3ef25
Publikováno v:
International Journal of Ophthalmology, Vol 17, Iss 7, Pp 1193-1204 (2024)
AIM: To address the challenges of data labeling difficulties, data privacy, and necessary large amount of labeled data for deep learning methods in diabetic retinopathy (DR) identification, the aim of this study is to develop a source-free domain ada
Externí odkaz:
https://doaj.org/article/f3915f9c74ca46018587032a28bb4265
Publikováno v:
Complex & Intelligent Systems, Vol 10, Iss 5, Pp 6379-6408 (2024)
Abstract Predicting student performance is crucial for both preventing failure and enabling personalized teaching-and-learning strategies. The digitalization of educational institutions has led to the collection of extensive student learning data ove
Externí odkaz:
https://doaj.org/article/4d079369ead04150a0a5116779d3f6a4
Publikováno v:
Software, Vol 3, Iss 2, Pp 227-249 (2024)
This study introduces a novel framework, “Comprehensive Optimization and Refinement through Ensemble Fusion in Domain Adaptation for Person Re-identification (CORE-ReID)”, to address an Unsupervised Domain Adaptation (UDA) for Person Re-identific
Externí odkaz:
https://doaj.org/article/2905f436c60d4f2a93a25909cba8edaf