Convolutional Neural Networks
OverFeat
Introduced by Sermanet et al. in OverFeat: Integrated Recognition, Localization and Detection using Convolutional NetworksOverFeat is a classic type of convolutional neural network architecture, employing convolution, pooling and fully connected layers. The Figure to the right shows the architectural details.
Source: OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| General Classification | 2 | 18.18% |
| Image Classification | 2 | 18.18% |
| Object Detection | 2 | 18.18% |
| Object Recognition | 2 | 18.18% |
| Retrieval | 1 | 9.09% |
| BIG-bench Machine Learning | 1 | 9.09% |
| Face Recognition | 1 | 9.09% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
Convolution
|
Convolutions | |
Dense Connections
|
Feedforward Networks | |
Dropout
|
Regularization | |
Max Pooling
|
Pooling Operations | |
ReLU
|
Activation Functions | |
Softmax
|
Output Functions |
