DPNET: Dual-Path Network for Efficient Object Detection with Lightweight Self-Attention

Abstract

Object detection often costs a considerable amount of computation to get satisfied performance, which is unfriendly to be deployed in edge devices. To address the trade-off between computational cost and detection accuracy, this paper presents a dual path network, named DPNet, for efficient object detection with lightweight self-attention. In backbone, a single input/output lightweight self-attention module (LSAM) is designed to encode global interactions between different positions. LSAM is also extended into a multiple-inputs version in feature pyramid network (FPN), which is employed to capture cross-resolution dependencies in two paths. Extensive experiments on the COCO dataset demonstrate that our method achieves promising detection results. More specifically, DPNet obtains 29.0% AP on COCO test-dev, with only 1.14 GFLOPs and 2.27M model size for a 320 × 320 image.

A Novel Lightweight Object Detection Network with Attention Modules and Hierarchical Feature Pyramid

“…The objective is to localize and classify specific objects in an image, accurately find all the objects of interest, and locate the position with a rectangular bounding box [2,3]. In recent years, in the field of computer vision, there has been a growing focus on designing deeper networks to extract valuable feature information, resulting in improved performance [4][5][6][7][8]. However, due to the vast number of parameters in these models, they often consume a significant amount of computational resources.…”