Now showing items 1-4 of 4

    • Exploring the role of loss functions in biomedical image segmentation 

      Zhao, Di; Tang, Yi; Gourinovitch, A.; Liankova, A. (БНТУ, 2023)
      The loss function is an important part of the segmentation method based on deep learning, and the improvement of the loss function can improve the segmentation effect of the network from the root, however, there are few literatures to do specific analysis and summary of various types of loss functions, this paper summaries some commonly used loss functions from the common problems ...
      2023-11-11
    • Human physical activity recognition system 

      Zhao, Di; Tang, Yi (БНТУ, 2022)
      Human activity recognition (HAR) is a technique that somehow senses the human activities, analyzes the relevant information, and identifies the corresponding behaviors mode. This text introduces a kind of human physical activity recognition system based on frequency features.
      2023-01-24
    • Mask-embedding and feature-fused network for medical image segmentation 

      Tang, Yi; Zhao, Di; Gourinovitch, A. (БНТУ, 2023)
      Medical image segmentation has a vital role in disease diagnosis and treatment. The feature enhancement module and a mask embedding block for medical image segmentation is proposed. This method utilizes an encoder-decoder architecture with attention mechanism and residual connections to adaptively adjust the importance of each layer of features. The proposed network achieves ...
      2023-11-11
    • Real-time object detection based on CNN 

      Tang, Yi; Zhao, Di (БНТУ, 2022)
      Computer vision, also known as CV, which can gain high-level understanding from digital images or videos. The real-time object detection has been used in many fields, such as people counting, unmanned supermarket, photo focus in cameras and so on. This paper introduces the difficulties in real-time object detection and developments and applications in China.
      2023-01-26