CornerNet-Lite: Efficient Keypoint Based Object Detection

18 Apr 2019Hei LawYun TengOlga RussakovskyJia Deng

Keypoint-based methods are a relatively new paradigm in object detection, eliminating the need for anchor boxes and offering a simplified detection framework. Keypoint-based CornerNet achieves state of the art accuracy among single-stage detectors... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Real-Time Object Detection COCO CornerNet-Squeeze MAP 34.4 # 8
FPS 33 # 8
Object Detection COCO minival CornerNet-Saccade (Hourglass-104) box AP 41.4 # 35
APS 23.8 # 26
APM 43.5 # 28
APL 57.1 # 16
Object Detection COCO minival CornerNet-Saccade (Hourglass-54) box AP 42.6 # 29
APS 25.5 # 20
APM 44.3 # 23
APL 58.4 # 13
Object Detection COCO test-dev CornerNet-Squeeze box AP 34.4 # 76
Object Detection COCO test-dev CornerNet-Saccade (Hourglass-104, multi-scale) box AP 43.2 # 35
APS 24.4 # 42
APM 44.6 # 43
APL 57.3 # 24