Abstract

Large number of ReLU and MAC operations of Deep neural networks make them ill-suited for latency and compute-efficient private inference. In this paper, we present a model optimization method that allows a model to learn to be shallow. In particular, we leverage the ReLU sensitivity of a convolutional block to remove a ReLU layer and merge its succeeding and preceding convolution layers to a shallow block. Unlike existing ReLU reduction methods, our joint reduction method can yield models with improved reduction of both ReLUs and linear operations by up to 1.73 x and 1.47 x, respectively, evaluated with ResNet18 on CIFAR-100 without any significant accuracy-drop.

Date

November 30, 2025

Authors

Souvik Kundu, Yuke Zhang, Dake Chen, Peter A Beerel

Conference

Proceedings of the IEEE/CVF conference on computer vision and pattern recognition

Pages

4685-4689