Convolutional Neural Networks
Harm-Net
Introduced by Ulicny et al. in Harmonic Convolutional Networks based on Discrete Cosine TransformA Harmonic Network, or Harm-Net, is a type of convolutional neural network that replaces convolutional layers with "harmonic blocks" that use Discrete Cosine Transform (DCT) filters. These blocks can be useful in truncating high-frequency information (possible due to the redundancies in the spectral domain).
Source: Harmonic Convolutional Networks based on Discrete Cosine Transform
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Edge Detection | 1 | 25.00% |
| Image Classification | 1 | 25.00% |
| Object Detection | 1 | 25.00% |
| Semantic Segmentation | 1 | 25.00% |
Average Pooling
Dense Connections
Dropout
Harmonic Block
Max Pooling
ReLU
