SGE net: Video object detection with squeezed GRU and information entropy map
This work addresses efficiency and accuracy challenges in video object detection for computer vision applications, representing an incremental improvement.
The paper tackled video object detection by proposing SGE-Net, which combines a squeezed GRU and information entropy map to improve accuracy and reduce computational cost, achieving a 3.7 mAP increase and reducing parameters from 6.33 million to 0.67 million compared to a baseline.
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.