DeepAI AI Chat
Log In Sign Up

CenterNet: Object Detection with Keypoint Triplets

04/17/2019
by   Kaiwen Duan, et al.
0

In object detection, keypoint-based approaches often suffer a large number of incorrect object bounding boxes, arguably due to the lack of an additional look into the cropped regions. This paper presents an efficient solution which explores the visual patterns within each cropped region with minimal costs. We build our framework upon a representative one-stage keypoint-based detector named CornerNet. Our approach, named CenterNet, detects each object as a triplet, rather than a pair, of keypoints, which improves both precision and recall. Accordingly, we design two customized modules named cascade corner pooling and center pooling, which play the roles of enriching information collected by both top-left and bottom-right corners and providing more recognizable information at the central regions, respectively. On the MS-COCO dataset, CenterNet achieves an AP of 47.0%, which outperforms all existing one-stage detectors by a large margin. Meanwhile, with a faster inference speed, CenterNet demonstrates quite comparable performance to the top-ranked two-stage detectors. Code is available at https://github.com/Duankaiwen/CenterNet.

READ FULL TEXT

page 1

page 3

page 7

04/17/2019

CenterNet: Keypoint Triplets for Object Detection

In object detection, keypoint-based approaches often suffer a large numb...
04/18/2022

CenterNet++ for Object Detection

There are two mainstreams for object detection: top-down and bottom-up. ...
03/20/2020

CentripetalNet: Pursuing High-quality Keypoint Pairs for Object Detection

Keypoint-based detectors have achieved pretty-well performance. However,...
11/17/2022

DiffusionDet: Diffusion Model for Object Detection

We propose DiffusionDet, a new framework that formulates object detectio...
11/21/2020

One Metric to Measure them All: Localisation Recall Precision (LRP) for Evaluating Visual Detection Tasks

Despite being widely used as a performance measure for visual detection ...
05/22/2020

Hashing-based Non-Maximum Suppression for Crowded Object Detection

In this paper, we propose an algorithm, named hashing-based non-maximum ...
05/27/2021

PSRR-MaxpoolNMS: Pyramid Shifted MaxpoolNMS with Relationship Recovery

Non-maximum Suppression (NMS) is an essential postprocessing step in mod...

Code Repositories

CenterNet

an implement for CenterNet by keras and tensorflow


view repo

CenterNet-annotation

Codes for our paper "CenterNet: Keypoint Triplets for Object Detection" . 代码注释


view repo