Convolutions
Octave Convolution
Introduced by Chen et al. in Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave ConvolutionAn Octave Convolution (OctConv) stores and process feature maps that vary spatially “slower” at a lower spatial resolution reducing both memory and computation cost. It takes in feature maps containing tensors of two frequencies one octave apart, and extracts information directly from the low-frequency maps without the need of decoding it back to the high-frequency. The motivation is that in natural images, information is conveyed at different frequencies where higher frequencies are usually encoded with fine details and lower frequencies are usually encoded with global structures.
Source: Drop an Octave: Reducing Spatial Redundancy in Convolutional Neural Networks with Octave Convolution
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Object Detection | 1 | 5.26% |
| Image Super-Resolution | 1 | 5.26% |
| Super-Resolution | 1 | 5.26% |
| Tumor Segmentation | 1 | 5.26% |
| Denoising | 1 | 5.26% |
| Image Compression | 1 | 5.26% |
| Image Denoising | 1 | 5.26% |
| MS-SSIM | 1 | 5.26% |
| Semantic Segmentation | 1 | 5.26% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
