no code implementations • 13 Aug 2022 • Yiheng Lu, Ziyu Guan, Yaming Yang, Maoguo Gong, Wei Zhao, Kaiyuan Feng
By leveraging the proposed AFIE, the proposed framework is able to yield a stable importance evaluation of each filter no matter whether the original model is trained fully.
no code implementations • 9 Aug 2022 • Yiheng Lu, Maoguo Gong, Wei Zhao, Kaiyuan Feng, Hao Li
Therefore, we propose a sensitiveness based method to evaluate the importance of each layer from the perspective of inference accuracy by adding extra damage for the original model.