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 | 62 | 8.53% |
| General Classification | 42 | 5.78% |
| Super-Resolution | 37 | 5.09% |
| Object Detection | 29 | 3.99% |
| Classification | 26 | 3.58% |
| Image Super-Resolution | 23 | 3.16% |
| Semantic Segmentation | 21 | 2.89% |
| Style Transfer | 19 | 2.61% |
| Quantization | 18 | 2.48% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
Dense Connections
|
Feedforward Networks | |
Dropout
|
Regularization | |
Max Pooling
|
Pooling Operations | |
ReLU
|
Activation Functions | |
Softmax
|
Output Functions |
