Lightdet: A Lightweight and Accurate Object Detection Network
Qiankun Tang, Jie Li, Zhiping Shi, Yu Hu
Abstract
The extensive computational burden limits the usage of accurate but complex object detectors in resource-bounded scenarios. In this paper, we present a lightweight object detector, named LightDet, to address this dilemma. We design a lightweight backbone that is able to capture rich low-level features by the proposed Detail-Preserving Module. To effectively aggregate bottom and top-down features, we introduce an efficient Feature-Preserving and Refinement Module. A lightweight prediction head is employed to further reduce the entire network complexity. Experimental results show that our LightDet achieves 75.5% mAP on PASCAL VOC 2007 at the speed of 250 FPS and 24.0% mAP on MS COCO dataset.
Topics & Concepts
Pascal (unit)Computer scienceObject detectionDetectorBackbone networkObject (grammar)Feature (linguistics)Aggregate (composite)Feature extractionArtificial intelligencePattern recognition (psychology)Computer networkLinguisticsPhilosophyTelecommunicationsComposite materialProgramming languageMaterials scienceAdvanced Neural Network ApplicationsAdvanced Image and Video Retrieval TechniquesRemote-Sensing Image Classification