SGE net: Video object detection with squeezed GRU and information entropy map

TL;DR

This paper introduces SGE-Net, an efficient video object detection method that combines a channel-reduced GRU and an information entropy map, achieving higher accuracy with fewer parameters.

Contribution

The paper proposes a novel Squeezed GRU and entropy-based attention mechanism for improved efficiency and accuracy in video object detection.

Findings

mAP increased by 3.7 over baseline

Parameters reduced from 6.33M to 0.67M

Enhanced classification performance with entropy map

Abstract

Recently, deep learning based video object detection has attracted more and more attention. Compared with object detection of static images, video object detection is more challenging due to the motion of objects, while providing rich temporal information. The RNN-based algorithm is an effective way to enhance detection performance in videos with temporal information. However, most studies in this area only focus on accuracy while ignoring the calculation cost and the number of parameters. In this paper, we propose an efficient method that combines channel-reduced convolutional GRU (Squeezed GRU), and Information Entropy map for video object detection (SGE-Net). The experimental results validate the accuracy improvement, computational savings of the Squeezed GRU, and superiority of the information entropy attention mechanism on the classification performance. The mAP has increased by 3.7 contrasted with the baseline, and the number of parameters has decreased from 6.33 million to 0.67 million compared with the standard GRU.