德克萨斯大学提出:One-stage目标检测最强算法 ExtremeNet
前戏
最近出了很多论文,各种SOTA。比如(点击可访问):
商汤等提出:统一多目标跟踪框架
亚马逊提出:用于人群计数的尺度感知注意力网络
今天头条推送的是目前人脸检测方向的SOTA论文:改进SRN人脸检测算法。本文要介绍的是目前(2019-01-26) one-stage目标检测中最强算法:ExtremeNet。
正文
《Bottom-up Object Detection by Grouping Extreme and Center Points》
arXiv: https://arxiv.org/abs/1901.08043
github: https://github.com/xingyizhou/ExtremeNet
作者团队:UT Austin
注:2019年01月23日刚出炉的paper
Abstract:With the advent of deep learning, object detection drifted from a bottom-up to a top-down recognition problem. State of the art algorithms enumerate a near-exhaustive list of object locations and classify each into: object or not. In this paper, we show that bottom-up approaches still perform competitively. We detect four extreme points (top-most, left-most, bottom-most, right-most) and one center point of objects using a standard keypoint estimation network. We group the five keypoints into a bounding box if they are geometrically aligned. Object detection is then a purely appearance-based keypoint estimation problem, without region classification or implicit feature learning. The proposed method performs on-par with the state-of-the-art region based detection methods, with a bounding box AP of 43.2% on COCO test-dev. In addition, our estimated extreme points directly span a coarse octagonal mask, with a COCO Mask AP of 18.9%, much better than the Mask AP of vanilla bounding boxes. Extreme point guided segmentation further improves this to 34.6% Mask AP.
Illustration of our object detection method
Illustration of our framework
Illustration of our object detection method
基础工作
Extreme and center points
Keypoint detection
CornerNet
Deep Extreme Cut
创新点
Center Grouping
Ghost box suppression
Edge aggregation
Extreme Instance Segmentation
实验结果
ExtremeNet有多强,看下面的图示就知道了,在COCO test-dev数据集上,mAP为43.2,在one-stage detector中,排名第一。可惜的是没有给出时间上的对比,论文中只介绍说测试一幅图像,耗时322ms(3.1 FPS)。
State-of-the-art comparison on COCO test-dev
想要了解最新最快最好的论文速递、开源项目和干货资料,欢迎加入CVer学术交流群。涉及图像分类、目标检测、图像分割、人脸检测&识别、目标跟踪、GANs、学术竞赛交流、Re-ID、风格迁移、医学影像分析、姿态估计、OCR、SLAM、场景文字检测&识别和超分辨率等方向。
- 目标检测算法的另一分支(one stage检测算法):YOLO、SSD、YOLOv2/YOLO 9000、YOLOv3
- 基于深度学习的目标检测算法——one stage & two stage
- FCOS: 最新的one-stage逐像素目标检测算法
- 深度学习目标检测算法综述(Two-stage,One-stage)
- 目标检测之one-stage和two-stage网络的区别
- 目标检测算法的演进(two-stage检测算法):R-CNN、SPP-Net、Fast R-CNN、Faster R-CNN、Mask R-CNN
- 【【DL学习笔记】【转】深度学习目标检测的整体架构描述(one-stage/two-stage/multi-stage)
- 增量学习不只有finetune,三星AI提出增量式少样本目标检测算法ONCE | CVPR 2020
- YOLOv1 解读:使用 unified system/ one-stage 实现目标检测
- 中科院和京东AI研究院提出:改进SRN人脸检测算法,目前业界最强!
- Two-stage目标检测里程碑算法之RCNN、SPP Net、Fast RCNN、Faster RCNN、FPN等
- 目标检测FCOS: Fully Convolutional One-Stage Object Detection论文详解
- 论文笔记:一阶段全卷积目标检测FCOS: Fully Convolutional One-Stage Object Detection
- 【深度学习理论】基于滑动窗口的目标检测算法
- 基于深度学习的目标检测算法综述
- CVPR2018 目标检测(object detection)算法总览
- 【图像处理】Haar Adaboost 检测自定义目标(视频车辆检测算法代码)
- 深度学习之目标检测常用算法原理+实践精讲完整教程百度云
- 运动目标跟踪与检测的源代码(CAMSHIFT 算法)
- 目标检测算法学习----YOLOv3