Results 1 to 10 of about 2,079,458 (324)

Attention and feature transfer based knowledge distillation [PDF]

Scientific Reports, 2023
Existing knowledge distillation (KD) methods are mainly based on features, logic, or attention, where features and logic represent the results of reasoning at different stages of a convolutional neural network, and attention maps symbolize the reasoning ...
Guoliang Yang, Shuaiying Yu, Yangyang Sheng, Hao Yang   +3 more
doaj   +4 more sources

Attention-based speech feature transfer between speakers [PDF]

Frontiers in Artificial Intelligence
In this study, we propose a simple yet effective method for incorporating the source speaker's characteristics in the target speaker's speech. This allows our model to generate the speech of the target speaker with the style of the source speaker.
Hangbok Lee, Minjae Cho, Hyuk-Yoon Kwon
doaj   +4 more sources

Semi-Supervised Instance-Segmentation Model for Feature Transfer Based on Category Attention [PDF]

Sensors, 2022
In the task of image instance segmentation, semi-supervised instance segmentation algorithms have received constant research attention over recent years.
Hao Wang, Juncai Liu, Changhai Huang, Xuewen Yang, Dasha Hu, Liangyin Chen, Xiaoqing Xing, Yuming Jiang   +7 more
doaj   +2 more sources

Joint Feature-Space and Sample-Space Based Heterogeneous Feature Transfer Method for Object Recognition Using Remote Sensing Images with Different Spatial Resolutions [PDF]

Sensors, 2021
To improve the classification results of high-resolution remote sensing images (RSIs), it is necessary to use feature transfer methods to mine the relevant information between high-resolution RSIs and low-resolution RSIs to train the classifiers together.
Wei Hu, Xiyuan Kong, Liang Xie, Huijiong Yan, Wei Qin, Xiangyi Meng, Ye Yan, Erwei Yin   +7 more
doaj   +2 more sources

Author Correction: Attention and feature transfer based knowledge distillation. [PDF]

Sci Rep, 2023
Yang G, Yu S, Sheng Y, Yang H.
europepmc   +3 more sources

Partial Transfer Learning Method Based on Inter-Class Feature Transfer for Rolling Bearing Fault Diagnosis [PDF]

Sensors
Rolling bearing fault diagnosis methods based on transfer learning always assume that the sample classes in the target domain are consistent with those in the source domain during the training phase.
Hongbo Que, Xuyan Liu, Siqin Jin, Yaoyan Huo, Chengpan Wu, Chuancang Ding, Zhongkui Zhu   +6 more
doaj   +2 more sources

The Transmission of Substrate Features

Journal of Modern Languages, 2020
Theories of the formation of creole syntax have been proposed to explain whether substrates and superstrates influence the resultant creole structures, and if so, what the mechanisms are by which they influence them.
Robert Laub
doaj   +14 more sources

Fuzzy Inference and Manifold Regularization Combined Feature Transfer Learning

Jisuanji kexue yu tansuo, 2020
Transfer learning leverages the rich data in the source domain to provide support for building accurate models in the target domain. Feature transfer learning is a kind of widely studied technology in transfer learning, but the existing feature transfer ...
SONG Yixuan, DENG Zhaohong, QIN Bin
doaj   +1 more source

Imbalanced Fault Diagnosis of Rolling Bearing Using Data Synthesis Based on Multi-Resolution Fusion Generative Adversarial Networks

Machines, 2022
Fault diagnosis of industrial bearings plays an invaluable role in the health monitoring of rotating machinery. In practice, there is far more normal data than faulty data, so the data usually exhibit a highly skewed class distribution.
Chuanzhu Hao, Junrong Du, Haoran Liang
doaj   +1 more source

Person Re-identification Combined with Clothing Information Transfer

Jisuanji kexue yu tansuo, 2021
Person re-identification (Re-ID) is an identification method based on the overall characteristics of human body, which is usually used to judge whether there is a specific person in the image or video sequence.
YUAN Chunmiao, NIU Ying, GUO Tao, LI Xin
doaj   +1 more source