Scale-Aware Squeeze-and-Excitation for Lightweight Object Detection
Zhihua Xu, Xiaobin Hong, Tianshui Chen, Zhijing Yang, Yukai Shi
Abstract
Lightweight object detection can promote intelligent robotics to recognize surroundings objects with limited computational resources, and thus receives increasing attention in robotics communities. Recently, high-resolution networks (HRNets) can learn high-resolution representation and it obtains excellent performance as the backbones of current cutting-edge object detectors. However, two crucial issues remain with regard to applying HRNet-based detectors to mobile devices—insufficient local feature interactions and multiscale feature fusion. In this work, we propose a scale-aware squeeze-and-excitation (SASE) module that utilizes SE operations to fully explore feature interactions without increasing network complexity; this is followed by a scale-aware attention (SAA) mechanism, which adaptively fuses multiscale features by estimating the importance of each scale. The SASE module can serve as the basic block for the HRNet, which facilitates the use of HRNet as a backbone for lightweight object detection. Extensive experiments conducted on Microsoft COCO and Pascal VOC demonstrate that the proposed method has a good tradeoff between accuracy and model complexity. With similar numbers of parameters and calculations, the mean average precision (mAP) achieved on the COCO dataset is improved by 3.7% over that of Lite-HRNet.