论文阅读
张家坎
这个作者很懒,什么都没留下…
展开
-
目标检测系列论文阅读
该图链接:https://github.com/hoya012/deep_learning_object_detection#2014打算从一篇总结(Deep Learning for Generic Object Detection: A Survey)开始,然后顺着上图依次理顺一下。Deep Learning for Generic Object Detection: A Survey...原创 2019-02-06 12:58:14 · 1976 阅读 · 0 评论 -
FPN:Feature Pyramid Networks for Object Detection
论文:Feature Pyramid Networks for Object Detectionunofficial code - caffe:https://github.com/unsky/FPN1.识别不同大小的物体是计算机视觉中的一个基本挑战,我们知道,低层的特征语义信息比较少,但是目标位置准确;高层的特征语义信息比较丰富,但是目标位置比较粗略。所以,本文打算利用卷积网络的特征层级...原创 2019-02-12 11:37:23 · 343 阅读 · 0 评论 -
YOLO v2--YOLO9000: Better, Faster, Stronger
论文:YOLO9000: Better, Faster, Strongerofficial code - c:https://pjreddie.com/darknet/yolo/unofficial code - caffe:https://github.com/quhezheng/caffe_yolo_v2unofficial code - tensorflow:https://githu...转载 2019-02-12 10:18:16 · 1081 阅读 · 5 评论 -
R-FCN: Object Detection via Region-based Fully Convolutional Networks
论文:R-FCN: Object Detection via Region-based Fully Convolutional Networksofficial code - caffe:https://github.com/daijifeng001/R-FCNunofficial code - caffe:https://github.com/YuwenXiong/py-R-FCN1.提...原创 2019-02-11 10:54:30 · 266 阅读 · 0 评论 -
SSD: Single Shot MultiBox Detector
论文:SSD: Single Shot MultiBox Detectorofficial code - caffe:https://github.com/weiliu89/caffe/tree/ssdunofficial code - tensorflow:https://github.com/balancap/SSD-Tensorflowunofficial code - pytorch...原创 2019-02-09 12:04:15 · 282 阅读 · 0 评论 -
YOLO v1--You Only Look Once: Unified, Real-Time Object Detection
论文:You Only Look Once: Unified, Real-Time Object Detectionofficial code - c:https://pjreddie.com/darknet/yolo/1.YOLO 之前的物体检测方法主要是通过 region proposal 产生大量的可能包含待检测物体的 potential bounding box,再用分类器去判断每个...原创 2019-02-08 20:34:43 · 296 阅读 · 0 评论 -
OHEM:Training Region-based Object Detectors with Online Hard Example Mining
论文:Training Region-based Object Detectors with Online Hard Example Miningofficial code - caffe:https://github.com/abhi2610/ohem1. hard example顾名思义,难例,即检测困难的正样本,与 easy example相对,一般指训练过程中误分的样本。2. 核心...原创 2019-02-07 17:53:05 · 469 阅读 · 0 评论 -
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
论文:Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networksofficial code - caffe:https://github.com/rbgirshick/py-faster-rcnnunofficial code - tensorflow:https://github.com/end...原创 2019-02-07 16:01:51 · 282 阅读 · 0 评论 -
Fast R-CNN
论文:Fast R-CNNofficial code - caffe:https://github.com/rbgirshick/fast-rcnn检测要求的精确定位目标导致复杂性产生,其中两个主要挑战是:(1)必须处理大量候选目标区域(proposals);(2)这些候选框只提供了粗略定位,必须进行精修来精准定位。而解决这些问题的办法往往牺牲了速度、准确率或者简易性。1.1 R-CN...原创 2019-02-07 13:57:15 · 193 阅读 · 0 评论 -
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
论文:OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networksofficial code - torch:https://github.com/sermanet/OverFeat本文展示了一种整合了分类、定位和检测的神经网络框架。在 ConvNet 下利用 multisc...原创 2019-02-06 22:14:57 · 212 阅读 · 0 评论 -
R-CNN: Regions with CNN features
论文:Rich feature hierarchies for accurate object detection and semantic segmentationofficial code - caffe: https://github.com/rbgirshick/rcnn结合了两个关键技术(1)可以在自下而上的 region proposal 上应用大型卷积神经网络(CNNs)来定...原创 2019-02-06 15:43:31 · 858 阅读 · 0 评论 -
RetinaNet--Focal Loss for Dense Object Detection
首页:https://blog.csdn.net/u014236392/article/details/86767950论文:Focal Loss for Dense Object Detectionofficial code - keras:https://github.com/fizyr/keras-retinanetunofficial code - pytorch:https://g...原创 2019-02-12 22:40:44 · 497 阅读 · 0 评论