Interpreting and Disentangling Feature Components of Various Complexity from DNNs
This work addresses the challenge of interpreting DNN features for researchers and practitioners, offering a generic mathematical tool to analyze network compression and knowledge distillation, though it appears incremental in its approach.
The paper tackles the problem of defining and quantifying feature complexity in deep neural networks (DNNs) by proposing a method to disentangle feature components of different complexity orders and designing metrics to evaluate their reliability, effectiveness, and over-fitting significance, resulting in the discovery of a close relationship between feature complexity and DNN performance.
This paper aims to define, quantify, and analyze the feature complexity that is learned by a DNN. We propose a generic definition for the feature complexity. Given the feature of a certain layer in the DNN, our method disentangles feature components of different complexity orders from the feature. We further design a set of metrics to evaluate the reliability, the effectiveness, and the significance of over-fitting of these feature components. Furthermore, we successfully discover a close relationship between the feature complexity and the performance of DNNs. As a generic mathematical tool, the feature complexity and the proposed metrics can also be used to analyze the success of network compression and knowledge distillation.