Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp011831cn814
DC FieldValueLanguage
dc.contributor.authorTeng, Yun-
dc.date.accessioned2019-09-04T17:50:22Z-
dc.date.available2019-09-04T17:50:22Z-
dc.date.created2019-05-06-
dc.date.issued2019-09-04-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/dsp011831cn814-
dc.description.abstractCornerNet is a new approach to object detection that involves predicting bounding boxes as paired top-left and bottom-right keypoints. Having outperformed all existing one-stage detectors on COCO, CornerNet demonstrates that anchor boxes are not necessary, or even desirable. One major drawback of keypoint-based methods is that the improved accuracy comes at a high processing cost, and in its current state, CornerNet is prohibitively slow in applications requiring real-time detection. We address CornerNet’s inefficiency by using smaller feature maps 1/64 the size of the input image, replacing the residual module of the Hourglass backbone with a depthwise fire module, and re-implementing corner pooling to make better use of GPU parallelism. Our new lightweight CornerNet runs at 30ms on a GTX 1080Ti and achieves 34.4 AP on COCO, outperforming YOLOv3.en_US
dc.format.mimetypeapplication/pdf-
dc.language.isoenen_US
dc.titleFast CornerNet for Real-time Systemsen_US
dc.typePrinceton University Senior Theses-
pu.date.classyear2019en_US
pu.departmentComputer Scienceen_US
pu.pdf.coverpageSeniorThesisCoverPage-
pu.contributor.authorid961192178-
Appears in Collections:Computer Science, 1988-2021

Files in This Item:
File Description SizeFormat