Very Deep Convolutional Networks for Large-Scale Image Recognition
Citations
1,703 citations
Cites background or methods from "Very Deep Convolutional Networks fo..."
...The encoder is a vanilla CNN (such as VGG16 [13]) which is trained to classify the input, while the decoder is used to upsample the output of the encoder [12, 19, 20, 21, 22]....
[...]
...Unlike in fully convolutional networks (FCN) [12], fully connected layers of VGG16 were discarded in the latest incarnation of SegNet, in order to reduce the number of floating point operations and memory footprint, making it the smallest of these networks....
[...]
...All these works are based on a VGG16 [13] architecture, which is a very large model designed for multi-class classification....
[...]
1,702 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...We train three types of common networks: 1) all convolutional network (AllConv) [22]; 2) network in network (NiN) [13]; and 3) VGG16 network [21] as target image classifiers on CIFAR-10 dataset [12], [63]....
[...]
1,695 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...With promising results on AlexNet, we also looked at a larger, more recent network, VGG-16 [27], on the same ILSVRC-2012 dataset....
[...]
1,677 citations
Cites methods from "Very Deep Convolutional Networks fo..."
...Since the task is closely related to semantic labeling, most works have built upon the most successful architectures of the ImageNet Large Scale Visual Recognition Challenge (ILSVRC) [28], often initializing their networks with AlexNet [14] or the deeper VGG [31]....
[...]
...We investigate popular architectures (AlexNet [14], VGG-16 [31]) as the contractive part, since their pre-trained weights facilitate convergence....
[...]
1,649 citations
References
49,639 citations
21,729 citations
9,803 citations
9,775 citations
6,061 citations