Global Contextual Dependency Network for Object Detection

Junda Li, Chunxu Zhang and Bo Yang
Additional contact information
Junda Li: College of Computer Science and Technology, Jilin University, Changchun 130012, China
Chunxu Zhang: College of Computer Science and Technology, Jilin University, Changchun 130012, China
Bo Yang: College of Computer Science and Technology, Jilin University, Changchun 130012, China

Future Internet, 2022, vol. 14, issue 1, 1-10

Abstract: Current two-stage object detectors extract the local visual features of Regions of Interest (RoIs) for object recognition and bounding-box regression. However, only using local visual features will lose global contextual dependencies, which are helpful to recognize objects with featureless appearances and restrain false detections. To tackle the problem, a simple framework, named Global Contextual Dependency Network (GCDN), is presented to enhance the classification ability of two-stage detectors. Our GCDN mainly consists of two components, Context Representation Module (CRM) and Context Dependency Module (CDM). Specifically, a CRM is proposed to construct multi-scale context representations. With CRM, contextual information can be fully explored at different scales. Moreover, the CDM is designed to capture global contextual dependencies. Our GCDN includes multiple CDMs. Each CDM utilizes local Region of Interest (RoI) features and single-scale context representation to generate single-scale contextual RoI features via the attention mechanism. Finally, the contextual RoI features generated by parallel CDMs independently are combined with the original RoI features to help classification. Experiments on MS-COCO 2017 benchmark dataset show that our approach brings continuous improvements for two-stage detectors.

Keywords: object detection; global contextual dependency; multi-scale representations; attention mechanism (search for similar items in EconPapers)
JEL-codes: O3 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1999-5903/14/1/27/pdf (application/pdf)
https://www.mdpi.com/1999-5903/14/1/27/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jftint:v:14:y:2022:i:1:p:27-:d:723453

Access Statistics for this article

Future Internet is currently edited by Ms. Grace You

More articles in Future Internet from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().