Frequency Regularization: Reducing Information Redundancy in Convolutional Neural Networks

1 code implementation • IEEE Access 2023 • Chenqiu Zhao, Guanfang Dong, Shupei Zhang, Zijie Tan, Anup Basu

Since high-frequency components of images are known to be less critical, a large proportion of these parameters can be set to zero when networks are trained with the proposed frequency regularization.

Affine-Transformation-Invariant Image Classification by Differentiable Arithmetic Distribution Module

no code implementations • 1 Sep 2023 • Zijie Tan, Guanfang Dong, Chenqiu Zhao, Anup Basu

On this foundation, we present a novel Differentiable Arithmetic Distribution Module (DADM), which is designed to extract the intrinsic probability distributions from images.

Density Estimation Image Classification

Frequency Regularization: Restricting Information Redundancy of Convolutional Neural Networks

1 code implementation • 17 Apr 2023 • Chenqiu Zhao, Guanfang Dong, Shupei Zhang, Zijie Tan, Anup Basu

Since high frequency components of images are known to be less critical, a large proportion of these parameters can be set to zero when networks are trained with the proposed frequency regularization.