Sample-adaptive classification inference network

HIGHLIGHTS

• What: The authors propose a sample-adaptive training and inference model. The paper presents a classifier based on the Attention on Attention structure (AOA) to improve the correlation between output and query. Its core structure includes the self-attention mechanism, which allows the model to focus on information at different locations when processing sequence data, assigning inputs to different locations by calculating attention scores. The authors propose a complex sample extraction module to address this problem.
• Who: Juan Yang from the School of Computer and Information, Hefei University of Technology, Danxia Road, Hefei, Anhui, China . . .
  

   

  

  If you want to have access to all the content you need to log in!

  Thanks :)

  Username or E-mail:

  If you don't have an account, you can create one here.