2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection

2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection

ID:40705817

大小:673.09 KB

页数:10页

时间:2019-08-06

2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection_第1页
2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection_第2页
2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection_第3页
2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection_第4页
2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection_第5页
资源描述:

《2015_CVPR_Deepid-net Deformable deep convolutional neural networks for object detection》由会员上传分享,免费在线阅读,更多相关内容在学术论文-天天文库

1、DeepID-Net:DeformableDeepConvolutionalNeuralNetworksforObjectDetectionWanliOuyang,XiaogangWang,XingyuZeng,ShiQiu,PingLuo,YonglongTian,HongshengLi,ShuoYang,ZheWang,Chen-ChangeLoy,XiaoouTangTheChineseUniversityofHongKongwlouyang,xgwang@ee.cuhk.edu.hkAbstractPretrain

2、edonobject-levelannoationPretrainedonimage-levelannotationInthispaper,weproposedeformabledeepconvolutionalImageneuralnetworksforgenericobjectdetection.Thisnewdeeplearningobjectdetectionframeworkhasinnovationsinmultipleaspects.Intheproposednewdeeparchitecture,Visua

3、lizedmodelanewdeformationconstrainedpooling(def-pooling)layermodelsthedeformationofobjectpartswithgeometriccon-(a)straintandpenalty.Anewpre-trainingstrategyisproposedDeepmodelDeformablepatternExamplestolearnfeaturerepresentationsmoresuitablefortheobject...detectio

4、ntaskandwithgoodgeneralizationcapability.Bychangingthenetstructures,trainingstrategies,addingandremovingsomekeycomponentsinthedetectionpipeline,Patternasetofmodelswithlargediversityareobtained,whichDeformationsignificantlyimprovestheeffectivenessofmodelaverag-...pe

5、naltying.TheproposedapproachimprovesthemeanaveragedprecisionobtainedbyRCNN[14],whichwasthestate-of-Patternthe-art,from31%to50.3%ontheILSVRC2014detectiontestset.ItalsooutperformsthewinnerofILSVRC2014,DeformationpenaltyGoogLeNet,by6.1%.Detailedcomponent-wiseanalysis

6、(b)isalsoprovidedthroughextensiveexperimentalevaluation,Figure1.Themotivationofthispaperinnewpretrainingschemewhichprovideaglobalviewforpeopletounderstandthe(a)andjointlylearningfeaturerepresentationanddeformableob-deeplearningobjectdetectionpipeline.jectpartsshar

7、edbymultipleobjectclassesatdifferentsemanticlevels(b).In(a),amodelpretrainedonimage-levelannotationismorerobusttosizeandlocationchangewhileamodelpretrainedonobject-levelannotationisbetterinrepresentingobjectswith1.Introductiontightboundingboxes.In(b),whenipodrotat

8、es,itscircularpatternmoveshorizontallyatthebottomoftheboundingbox.Therefore,Objectdetectionisoneofthefundamentalchallengesinthecircularpatternshavesmall

当前文档最多预览五页,下载文档查看全文

此文档下载收益归作者所有

当前文档最多预览五页,下载文档查看全文
温馨提示:
1. 部分包含数学公式或PPT动画的文件,查看预览时可能会显示错乱或异常,文件下载后无此问题,请放心下载。
2. 本文档由用户上传,版权归属用户,天天文库负责整理代发布。如果您对本文档版权有争议请及时联系客服。
3. 下载前请仔细阅读文档内容,确认文档内容符合您的需求后进行下载,若出现内容与标题不符可向本站投诉处理。
4. 下载文档时可能由于网络波动等原因无法下载或下载错误,付费完成后未能成功下载的用户请联系客服处理。