Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
1,886 citations
1,777 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...A standard CNN architecture comprises fully connected layers and a number of blocks consisting of convolution kernels, activation function layer and max pooling [22, 23, 24]....
[...]
1,733 citations
Cites background or result from "Very Deep Convolutional Networks fo..."
...Both GoogLeNet [20] and VGG [31], described above, adopted quite large networks, 22 layers and 19 layers respectively, demonstrating that increasing the size is beneficial for image recognition accuracy....
[...]
...AlexNet [6] 2012 1st Five convolutional layersþthree fully connected layers An important CNN architecture which set the tone for many computer vision researchers Clarifai [52] 2013 1st Five convolutional layersþthree fully connected layers Insight into the function of intermediate feature layers SPP [26] 2014 3rd Five convolutional layersþthree fully connected layers Proposed the “spatial pyramid pooling” to remove the requirement of image resolution VGG [31] 2014 2nd Thirteen/fifteen convolutional layersþthree fully connected layers A thorough evaluation of networks of increasing depth...
[...]
...Along with the improvements of the classical CNN model, another characteristic shared by the top-performing models is that the architectures became deeper, as shown by GoogLeNet [20] (rank 1 in ILSVRC 2014) and VGG [31] (rank 2 in ILSVRC 2014), which achieved 6.67% and 7.32% respectively....
[...]
...Nevertheless, there are approaches [18,27,146] that deliver better performance by training on other models, e.g. Clarifai [52], GoogLeNet [20], and VGG [31]....
[...]
...In contrast to AlexNet, VGG [31] increased the depth of the network by adding more convolutional layers and taking advantage of very small convolutional filters in all layers....
[...]
1,729 citations
Cites background from "Very Deep Convolutional Networks fo..."
...models (Simonyan and Zisserman, 2014; Szegedy et al., 2015; He et al., 2016) and shown their effectiveness on large vision datasets (Deng et al....
[...]
1,705 citations
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations