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

TL;DR

DPNet introduces a dual-path network with lightweight self-attention modules to achieve efficient object detection, balancing high accuracy with low computational cost suitable for edge devices.

Contribution

The paper proposes a novel dual-path network with lightweight self-attention modules, enhancing global and cross-resolution feature interactions for efficient detection.

Findings

Achieves 29.0% AP on COCO test-dev

Uses only 1.14 GFLOPs and 2.27M parameters

Outperforms existing lightweight detectors

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 state-of-the-art 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 320x320 image.