no code implementations • 2 Apr 2024 • Hai Su, ZhenWen Jian, Songsen Yu
Therefore, we propose a knowledge distillation method that addresses both the classification and regression tasks, incorporating a task significance strategy.
no code implementations • 4 Nov 2023 • Hai Su, Jiajun Hu, Songsen Yu
Meta learning is a promising technique for solving few-shot fault prediction problems, which have attracted the attention of many researchers in recent years.
1 code implementation • 22 Nov 2022 • Jun Liang, Songsen Yu, Huan Yang
ResNets and its variants play an important role in various fields of image recognition.
no code implementations • 24 Mar 2022 • Hai Su, Meiyin Han, Junle Liang, Songsen Yu
In this paper, to enhance embed-ding signals, we study the insufficiencies of activation function, filters and loss function from the aspects of reduce embedding signal loss and enhance embedding signal capture ability.
no code implementations • 29 Dec 2021 • Hai Su, Shan Yang, Shuqing Zhang, Songsen Yu
Color image steganography based on deep learning is the art of hiding information in the color image.
no code implementations • 27 Dec 2021 • Hai Su, Meiyin Han, Junle Liang, Jun Liang, Songsen Yu
Compared with the traditional hashing methods, deep hashing methods generate hash codes with rich semantic information and greatly improves the performances in the image retrieval field.