Center Pooling

Introduced by Duan et al. in CenterNet: Keypoint Triplets for Object Detection

Center Pooling is a pooling technique for object detection that aims to capture richer and more recognizable visual patterns. The geometric centers of objects do not necessarily convey very recognizable visual patterns (e.g., the human head contains strong visual patterns, but the center keypoint is often in the middle of the human body).

The detailed process of center pooling is as follows: the backbone outputs a feature map, and to determine if a pixel in the feature map is a center keypoint, we need to find the maximum value in its both horizontal and vertical directions and add them together. By doing this, center pooling helps the better detection of center keypoints.

Source: CenterNet: Keypoint Triplets for Object Detection

Latest Papers

PAPER DATE
Efficient grouping for keypoint detection
Alexey SidnevEkaterina KrasikovaMaxim Kazakov
2020-10-23
DPAttack: Diffused Patch Attacks against Universal Object Detection
Shudeng WuTao DaiShu-Tao Xia
2020-10-16
Non-anchor-based vehicle detection for traffic surveillance using bounding ellipses
Byeonghyeop YuJohyun ShinGyeongjun KimSeungbin RohKeemin Sohn
2020-10-05
Object Detection and Tracking Algorithms for Vehicle Counting: A Comparative Analysis
Vishal MandalYaw Adu-Gyamfi
2020-07-31
DeepMark++: CenterNet-based Clothing Detection
Alexey SidnevAlexander KrapivinAlexey TrushkovEkaterina KrasikovaMaxim Kazakov
2020-06-01
Deep Active Learning for Remote Sensing Object Detection
Zhenshen QuJingda DuYong CaoQiuyu GuanPengbo Zhao
2020-03-17
DeepMark: One-Shot Clothing Detection
Alexey SidnevAlexey TrushkovMaxim KazakovIvan KorolevVladislav Sorokin
2019-10-02
Enhancing 2D Representation via Adjacent Views for 3D Shape Retrieval
Cheng Xu Zhaoqun Li Qiang Qiu Biao Leng Jingfei Jiang
2019-10-01
Object detection on aerial imagery using CenterNet
Dheeraj Reddy PaillaVarghese KollerathuSai Saketh Chennamsetty
2019-08-22
Deep High-Resolution Representation Learning for Visual Recognition
| Jingdong WangKe SunTianheng ChengBorui JiangChaorui DengYang ZhaoDong LiuYadong MuMingkui TanXinggang WangWenyu LiuBin Xiao
2019-08-20
CenterNet: Keypoint Triplets for Object Detection
| Kaiwen DuanSong BaiLingxi XieHonggang QiQingming HuangQi Tian
2019-04-17

Components

COMPONENT TYPE
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories