A lightweight convolutional network based on pruning algorithm for YOLO

Abstract

With the rapid development of deep learning, neural network models have become increasingly complicated, leading to larger storage space requirements and slower reasoning speed. These factors make it difficult to be deployed on resourcelimited platforms. To alleviate this problem, network pruning, an effective model compression method, is commonly performed in a deep neural network. However, traditional pruning methods simply set redundant weights to zero, thus failing to achieve the acceleration effect. In this paper, a channel-wise model scaling method is proposed to reduce the model size and speed up reasoning by structurally removing the redundant filters in convolutional layers. To make the residual block more sparse, we develop a pruning method for residual cells. Experimental results on the YOLOv3 detector show that our proposed approach achieves a 70.6% parameter compression ratio without compromising accuracy.

A Two-Stage Approach for Single Thermal Image Restoration

“…Zhang et al [31] have also made significant contributions in the field of few-shot learning methods. Meanwhile, Liu et al [32] have introduced a novel lightweight network designed specifically for deep learning applications. Additionally, in their groundbreaking work, Zhang et al [33] present an innovative approach for adaptive digital self-interference cancellation, which is particularly effective in denoising millimeter-wave signals.…”