Dynamic knowledge distillation with noise elimination for rgb-d salient object detection

HIGHLIGHTS

• who: Guangyu Ren and colleagues from the Department of Electrical and Electronic Engineering, Imperial College London, London , AZ, UK School of Electronic Engineering, Beijing University of Posts and Telecommunications, Beijing, China have published the paper: Dynamic Knowledge Distillation with Noise Elimination for RGB-D Salient Object Detection, in the Journal: Sensors 2022, 6188 of /2022/
• what: To tackle this dilemma the authors propose a distillation (DKD) method along with a lightweight structure which significantly reduces the computational burden while maintaining validity. The authors propose a novel dynamic distillation strategy, which can adaptively assign the distillation . . .
  

   

  

  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.