Skip Connection Blocks
Two-Way Dense Layer
Introduced by Wang et al. in Pelee: A Real-Time Object Detection System on Mobile DevicesTwo-Way Dense Layer is an image model block used in the PeleeNet architectures. Motivated by GoogLeNet, the 2-way dense layer is used to get different scales of receptive fields. One way of the layer uses a 3x3 kernel size. The other way of the layer uses two stacked 3x3 convolution to learn visual patterns for large objects.
Source: Pelee: A Real-Time Object Detection System on Mobile Devices
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 2 | 25.00% |
| Real-Time Object Detection | 2 | 25.00% |
| Computational Efficiency | 1 | 12.50% |
| Emotion Recognition | 1 | 12.50% |
| Facial Expression Recognition (FER) | 1 | 12.50% |
| Image Classification | 1 | 12.50% |
1x1 Convolution
Convolution
