馆藏&21903
TA的最新馆藏[转]&Deep Learning（36）
【目标识别】深度学习进行目标识别的资源列表：O网页链接 包括RNN、MultiBox、SPP-Net、DeepID-Net、Fast R-CNN、DeepBox、MR-CNN、Faster R-CNN、YOLO、DenseBox、SSD、Inside-Outside
Net、G-CNN等。
Deep Neural Networks for Object Detection
OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
ILSVRC 2013 mAP
intro: A deep version of the sliding window method, predicts bounding box directly from each location of the topmost feature map after knowing the confidences of the underlying object categories.
Rich feature hierarchies for accurate object detection and semantic segmentation(R-CNN)
VOC 2007 mAP
VOC 2010 mAP
VOC 2012 mAP
ILSVRC 2013 mAP
R-CNN,AlexNet
R-CNN,bbox reg,AlexNet
R-CNN,bbox reg,ZFNet
R-CNN,VGG-Net
R-CNN,bbox reg,VGG-Net
caffe-pr(“Make R-CNN the Caffe detection example”):
Scalable Object Detection using Deep Neural Networks (MultiBox)
intro: Train a CNN to predict Region of Interest.
Spatial Pyramid Pooling in Deep Convolutional Networks for Visual Recognition
VOC 2007 mAP
ILSVRC 2013 mAP
SPP_net(ZF-5),1-model
SPP_net(ZF-5),2-model
SPP_net(ZF-5),6-model
Learning Rich Features from RGB-D Images for Object Detection and Segmentation
Scalable, High-Quality Object Detection
DeepID-Net
DeepID-Net: Deformable Deep Convolutional Neural Networks for Object Detection
VOC 2007 mAP
ILSVRC 2013 mAP
DeepID-Net
Object Detection Networks on Convolutional Feature Maps
Trained on
NoC,+EB
NoC,+EB,bb
Improving Object Detection with Deep Convolutional Networks via Bayesian Optimization and Structured Prediction
VOC 2007 mAP(IoU&0.5)
R-CNN(AlexNet)
R-CNN(VGG)
+StructObj
+StructObj-FT
+StructObj+FGS
+StructObj-FT+FGS
VOC 2007 mAP(IoU&0.5)
R-CNN(AlexNet)
R-CNN(VGG)
+StructObj
+StructObj-FT
+StructObj+FGS
+StructObj-FT+FGS
Fast R-CNN
Fast R-CNN
VOC 2007 mAP
FRCN,VGG16
FRCN,VGG16
VOC 2010 mAP
FRCN,VGG16
FRCN,VGG16
07++12
VOC 2012 mAP
FRCN,VGG16
FRCN,VGG16
07++12
webcam demo:&
github(“Train Fast-RCNN on Another Dataset”):&
DeepBox: Learning Objectness with Convolutional Networks
Object detection via a multi-region & semantic segmentation-aware CNN model (MR-CNN)
Trained on
VOC 2007 mAP
Trained on
VOC 2012 mAP
code: “Pdf and code will appear here shortly – stay tuned”&
Faster R-CNN
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks(NIPS 2015)
training data
Faster RCNN, VGG-16
VOC 2007 test
Faster RCNN, VGG-16
VOC 2007 test
Faster RCNN, VGG-16
VOC 2007 test
Faster RCNN, VGG-16
07++12
VOC 2007 test
You Only Look Once: Unified, Real-Time Object Detection(YOLO)
intro: YOLO uses the whole topmost feature map to predict both confidences for multiple categories and bounding boxes (which are shared for these categories).
github(YOLO_tensorflow):&
R-CNN minus R
DenseBox: Unifying Landmark Localization with End to End Object Detection
KITTI result:&
SSD: Single Shot MultiBox Detector
Inside-Outside Net
Inside-Outside Net: Detecting Objects in Context with Skip Pooling and Recurrent Neural Networks
Detection results on VOC 2007 test:
07+12+S
07+12+S
07+12+S
Detection results on VOC 2012 test:
07++12
07++12
FRCN+YOLO
07++12
07++12
07+12+S
intro: “0.8s per image on a Titan X GPU (excluding proposal generation) without two-stage bounding-box regression and 1.15s per image with it”.
coco-leaderboard:&
G-CNN: an Iterative Grid Based Object Detector
Learning Deep Features for Discriminative Localization
homepage:&
github(Tensorflow):&
Factors in Finetuning Deep Model for object detection
We don’t need no bounding-boxes: Training object class detectors using only human verification
A MultiPath Network for Object Detection
Beyond Bounding Boxes: Precise Localization of Objects in Images (PhD Thesis)
homepage:&
phd-thesis:&
github(“SDS using hypercolumns”):&
T-CNN: Tubelets with Convolutional Neural Networks for Object Detection from Videos
Training Region-based Object Detectors with Online Hard Example Mining
Specific Object Deteciton
End-to-end people detection in crowded scenes
Convolutional Feature Maps: Elements of efficient (and accurate) CNN-based object detection
TensorBox: a simple framework for training neural networks to detect objects in images
intro: “The basic model implements the simple and robust GoogLeNet-OverFeat algorithm. We additionally provide an implementation of the&&algorithm”
Object detection in torch: Implementation of some object detection frameworks in torch
Convolutional Neural Networks for Object Detection
参考知识库
* 以上用户言论只代表其个人观点，不代表CSDN网站的观点或立场
访问：408749次
积分：7530
积分：7530
排名：第2303名
原创：330篇
转载：155篇
评论：195条
在读研究生，关注计算机视觉，机器学习，算法研究，医学病理图像，GPU编程等方向，努力学习C++、Matlab、Python、Opencv等语言中，希望结识更多同道中人，提升自己。