Convolutional Neural Networks
VGG
Introduced by Simonyan et al. in Very Deep Convolutional Networks for Large-Scale Image RecognitionVGG is a classical convolutional neural network architecture. It was based on an analysis of how to increase the depth of such networks. The network utilises small 3 x 3 filters. Otherwise the network is characterized by its simplicity: the only other components being pooling layers and a fully connected layer.
Image: Davi Frossard
Source: Very Deep Convolutional Networks for Large-Scale Image Recognition
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 60 | 8.82% |
| General Classification | 43 | 6.32% |
| Super-Resolution | 36 | 5.29% |
| Object Detection | 28 | 4.12% |
| Classification | 27 | 3.97% |
| Image Super-Resolution | 23 | 3.38% |
| Semantic Segmentation | 20 | 2.94% |
| Quantization | 18 | 2.65% |
| Style Transfer | 17 | 2.50% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
Dense Connections
|
Feedforward Networks | |
Dropout
|
Regularization | |
Max Pooling
|
Pooling Operations | |
ReLU
|
Activation Functions | |
Softmax
|
Output Functions |
