"Fast RCNN"의 두 판 사이의 차이
ph
잔글 (→Fast R-CNN) |
잔글 (→Fast R-CNN) |
||
| 1번째 줄: | 1번째 줄: | ||
=Fast R-CNN= | =Fast R-CNN= | ||
| − | 그냥 R-CNN은 이런가봄 : R-CNN first finetunes a ConvNet on object proposals using log loss. Then, it fits SVMs to ConvNet features. These SVMs act as object detectors, replacing the softmax classifier learnt by fine-tuning. In the third training stage, bounding-box regressors are learned. … Detection with VGG16 takes 47s / image (on a GPU). 이야 ~ | + | 그냥 R-CNN은 이런가봄 : R-CNN first finetunes a ConvNet on object proposals using log loss. Then, it fits SVMs to ConvNet features. These SVMs act as object detectors, replacing the softmax classifier learnt by fine-tuning. In the third training stage, bounding-box regressors are learned. … Detection with VGG16 takes 47s / image (on a GPU). 이야 ~ |
| + | |||
| + | 그냥 R-CNN은 object proposal마다 cnn forward하는데, SPPnets<ref name=r11>K.He, X.Zhang, S.Ren, and J.Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. In ECCV,2014.</ref>가 미리 cnn돌려놓고 거기서부터 feature뽑아내는 식으로 개선했다. | ||
2017년 8월 4일 (금) 14:19 판
Fast R-CNN
그냥 R-CNN은 이런가봄 : R-CNN first finetunes a ConvNet on object proposals using log loss. Then, it fits SVMs to ConvNet features. These SVMs act as object detectors, replacing the softmax classifier learnt by fine-tuning. In the third training stage, bounding-box regressors are learned. … Detection with VGG16 takes 47s / image (on a GPU). 이야 ~
그냥 R-CNN은 object proposal마다 cnn forward하는데, SPPnets[1]가 미리 cnn돌려놓고 거기서부터 feature뽑아내는 식으로 개선했다.
- ↑ K.He, X.Zhang, S.Ren, and J.Sun. Spatial pyramid pooling in deep convolutional networks for visual recognition. In ECCV,2014.