Can Knowledge Transfer Parameters Be Learned? LePoKet for Efficient Robotic Vision
The proposed LePoKet (Learnable Parameter Optimization for Knowledge Transfer), a structural transfer framework that embeds knowledge inheritance directly into the forward computation, demonstrates that learnable structural transfer generalizes across recognition and motion perception tasks and provides a promising app...
Y. C. Tchenko, Felix Mohr, H. Hadj-Abdelkader et al.
· 0 citations