Please use this identifier to cite or link to this item:
|Title:||Fast CornerNet for Real-time Systems|
|Abstract:||CornerNet 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.|
|Type of Material:||Princeton University Senior Theses|
|Appears in Collections:||Computer Science, 1988-2021|
Files in This Item:
|TENG-YUN-THESIS.pdf||2.44 MB||Adobe PDF||Request a copy|
Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.