GAR: Graph assisted reasoning for object detection

Zheng Li, Xiaocong Du, Yu Cao

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Scopus citations

Abstract

It is well believed that object-object relations and object-scene relations inherently improve the accuracy of object detection. However, the way to efficiently model relations remains a problem. Graph Convolutional Network (GCN), an effective method to handle structured data with relations, inspires us to leverage graphs in modeling relations for objection detection tasks. In this work, we propose a novel approach, Graph Assisted Reasoning (GAR), to utilize a heterogeneous graph in modeling object-object relations and object-scene relations. GAR fuses the features from neigh-boring object nodes as well as scene nodes and produces better recognition than that produced from individual object nodes. Moreover, compared to previous approaches using Recurrent Neural Network (RNN), the light-weight and low-coupling architecture of GAR further facilitates its integration into the object detection module. Comprehensive experiments on PASCAL VOC and MS COCO datasets demonstrate the efficacy of GAR.

Original languageEnglish (US)
Title of host publicationProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages1284-1293
Number of pages10
ISBN (Electronic)9781728165530
DOIs
StatePublished - Mar 2020
Externally publishedYes
Event2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020 - Snowmass Village, United States
Duration: Mar 1 2020Mar 5 2020

Publication series

NameProceedings - 2020 IEEE Winter Conference on Applications of Computer Vision, WACV 2020

Conference

Conference2020 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2020
Country/TerritoryUnited States
CitySnowmass Village
Period3/1/203/5/20

Bibliographical note

Funding Information:
This work was supported in part by C-BRIC, one of six centers in JUMP, a Semiconductor Research Corporation (SRC) program sponsored by DARPA. It is also partially support by National Science Foundation (CCF #1715443).

Publisher Copyright:
© 2020 IEEE.

Fingerprint

Dive into the research topics of 'GAR: Graph assisted reasoning for object detection'. Together they form a unique fingerprint.

Cite this