HIGHLIGHTS
- who: Wenhao Yuan et al. from the College of Big Data and Information Engineering, Guizhou University, Guiyang, China have published the paper: FCKDNet: A Feature Condensation Knowledge Distillation Network for Semantic Segmentation, in the Journal: Entropy 2023, 25, 125. of /2023/
- what: The authors investigate the output features of the teacher- student network and propose a feature condensation-based KD network (FCKDNet) which reduces pseudo-knowledge transfer in the teacher-student network. Combined with the pixel information entropy calculation rule the authors design a feature condensation method to separate the foreground feature knowledge from the . . .
If you want to have access to all the content you need to log in!
Thanks :)
If you don't have an account, you can create one here.