22. 29
DLによる物体検出1
• R-CNN(Region with CNN feature )
• “Rich feature hierarchies for accurate object detection and semantic segmentation” Girshick,
R., Donahue, J., Darrell, T., & Malik, J. /CVPR2014
• http://arxiv.org/pdf/1311.2524v5.pdf
• https://github.com/rbgirshick/rcnn
• Fast R-CNN/Faster R-CNN
• “Fast R-CNN” Girshick, R., ICCV2015
• http://arxiv.org/pdf/1504.08083v2.pdf
• https://github.com/rbgirshick/fast-rcnn (caffe)
• “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks ”
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, NIPS2015
• http://arxiv.org/pdf/1506.01497v3.pdf
•
DNNを用いた物体検出のベース論文
[弱点] 学習、推論ともに計算量が膨大
23. 30
DLによる物体検出2
• YOLO(You Only Look Once)
• “You Only Look Once: Unified, Real-Time Object Detection.,” J. K. Redmon, S. K. Divvala, R.
B. Girshick, and A. Farhadi
• http://arxiv.org/pdf/1506.02640v4.pdf
![29
DLによる物体検出1
• R-CNN(Region with CNN feature )
• “Rich feature hierarchies for accurate object detection and semantic segmentation” Girshick,
R., Donahue, J., Darrell, T., & Malik, J. /CVPR2014
• http://arxiv.org/pdf/1311.2524v5.pdf
• https://github.com/rbgirshick/rcnn
• Fast R-CNN/Faster R-CNN
• “Fast R-CNN” Girshick, R., ICCV2015
• http://arxiv.org/pdf/1504.08083v2.pdf
• https://github.com/rbgirshick/fast-rcnn (caffe)
• “Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks ”
Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun, NIPS2015
• http://arxiv.org/pdf/1506.01497v3.pdf
•
DNNを用いた物体検出のベース論文
[弱点] 学習、推論ともに計算量が膨大](https://image.slidesharecdn.com/20160902hyperscale04-160906022426/85/20160902-hyperscale-04-22-320.jpg)
