Bottom-up Object Detection by Grouping Extreme and Center Points 论文笔记

最新推荐文章于 2024-06-26 16:02:18 发布

Amusi（CVer）

最新推荐文章于 2024-06-26 16:02:18 发布

阅读量1.6k

点赞数

分类专栏：计算机视觉论文精读目标检测深度学习计算机视觉论文速递文章标签：深度学习机器学习计算机视觉目标检测人工智能

本文链接：https://blog.csdn.net/amusi1994/article/details/87461253

版权

计算机视觉论文速递同时被 3 个专栏收录

122 篇文章 189 订阅

订阅专栏

计算机视觉

42 篇文章 6 订阅

订阅专栏

目标检测

41 篇文章 16 订阅

订阅专栏

Summary：德克萨斯大学提出：One-stage目标检测最强算法 ExtremeNet
Author：Amusi
Date：2019-02-11
微信公众号：CVer
GitHub：https://github.com/amusi/TensorFlow-From-Zero-To-One
原文链接：德克萨斯大学提出：One-stage目标检测最强算法 ExtremeNet
知乎：https://zhuanlan.zhihu.com/p/55838614

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》
file

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.

file