Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
330 citations
330 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...The size of a feature map will be just 1/24 size of the original object when it arrives at the last convolutional layer of VGG16, and the feature map will be too coarse to classify such small instances....
[...]
...The fast R-CNN uses the VGG16 [83] model, in which the convolutional layers...
[...]
...The fast R-CNN uses the VGG16 [83] model, in which the convolutional layers 14 M.-M. Cheng, Y. Liu, W.-Y. Lin, et al. are pooled several times....
[...]
330 citations
330 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...The effects of style swapping in different layers of the VGG-19 network are shown in Figure 3....
[...]
...Here we describe our training of an inverse network that computes an approximate inverse function of the pretrained VGG-19 network [31]....
[...]
...Compared to optimization-based methods, our optimization formula is easier to solve and requires less time per iteration, likely due to only using one layer of the pretrained VGG-19 network....
[...]
...Figure 3: The effect of style swapping in different layers of VGG-19 [31], and also in RGB space....
[...]
329 citations
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations