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... This is wasteful, inefficient, and requires additional post-processing. In this paper, we take a different approach. We model an object as a single point --- the center point of its bounding box. Our detector uses keypoint estimation to find center points and regresses to all other object properties, such as size, 3D location, orientation, and even pose. Our center point based approach, CenterNet, is end-to-end differentiable, simpler, faster, and more accurate than corresponding bounding box based detectors. CenterNet achieves the best speed-accuracy trade-off on the MS COCO dataset, with 28.1% AP at 142 FPS, 37.4% AP at 52 FPS, and 45.1% AP with multi-scale testing at 1.4 FPS. We use the same approach to estimate 3D bounding box in the KITTI benchmark and human pose on the COCO keypoint dataset. Our method performs competitively with sophisticated multi-stage methods and runs in real-time. read more

PDF Abstract

Datasets


Results from the Paper


Ranked #17 on Real-Time Object Detection on COCO (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric Name Metric Value Global Rank Uses Extra
Training Data
Result Benchmark
Real-Time Object Detection COCO CenterNet Hourglass-104 MAP 42.1 # 17
FPS 7.8 # 24
inference time (ms) 128.2 # 13
Real-Time Object Detection COCO CenterNet DLA-34 + DCNv2 MAP 39.2 # 19
FPS 28 # 19
inference time (ms) 35 # 12
Object Detection COCO test-dev CenterNet-DLA (DLA-34, multi-scale) box AP 41.6 # 117
APS 21.5 # 124
APM 43.9 # 114
APL 56.0 # 84

Methods


No methods listed for this paper. Add relevant methods here