Object　detection　using　convolutional　neural　networks　addresses　the　recognition　problem　solely　in　terms　of　feature　extraction　and　disregards　knowledge　and　experience　to　explore　higher-level　relationships　between　objects.　This　paper　proposed　a　knowledge　graph　network　based　on　a　graph　convolution　network　to　improve　the　accuracy　of　baseline　detectors.　This　network　can　be　integrated　into　any　object　detection　framework.　First,　this　paper　created　an　experience　memory　module　to　store　information　about　categories　in　the　database.　When　inputting　the　image　to　the　database,　an　experience　vector　for　it　was　obtained.　The　experience　data　graph　was　then　constructed　by　counting　the　co-occurrences　of　labels　in　the　dataset.　Finally,　a　graph　convolutional　neural　network　was　used　to　extract　the　relationship　between　the　experience　vector　and　the　data　graph　matrix.　This　relational　pattern　can　help　the　baseline　detector　perform　better.　Several　classical　object　detectors　were　then　evaluated　using　the　COCO,　VOC,　and　KITTI　datasets.　The　results　indicated　a　significant　increase　for　the　baseline　detector　in　mAP　using　the　knowledge　graph　network.