A low functional redundancy-based network slimming method for accelerating deep neural networks

Today's article comes from the Alexandria Engineering Journal. The authors are Fang et al., from Ocean University, in China. In this paper they reveal a model-compression technique for CNNs and ViTs that seems to be capable of incredible efficiency.

DOI: 10.1016/j.aej.2024.12.118

Book
Book

Members Only

You must be an active Journal Club member to access this content. If you're already a member, click the blue button to login. If you're not a member yet, click the sign-up button to get started.

Login to My Account Sign Up