Objects as Points

16 Apr 2019 Xingyi Zhou Dequan Wang Philipp Krähenbühl

Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Real-Time Object Detection COCO CenterNet DLA-34 + DCNv2 MAP 39.2 # 10
FPS 28 # 11
inference time (ms) 35 # 10
Real-Time Object Detection COCO CenterNet Hourglass-104 MAP 42.1 # 8
FPS 7.8 # 13
inference time (ms) 128.2 # 11
Object Detection COCO test-dev CenterNet-DLA (DLA-34, multi-scale) box AP 41.6 # 52
APS 21.5 # 68
APM 43.9 # 58
APL 56.0 # 40

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet