Downsampling
Anti-Alias Downsampling
Introduced by Zhang in Making Convolutional Networks Shift-Invariant AgainAnti-Alias Downsampling (AA) aims to improve the shift-equivariance of deep networks. Max-pooling is inherently composed of two operations. The first operation is to densely evaluate the max operator and second operation is naive subsampling. AA is proposed as a low-pass filter between them to achieve practical anti-aliasing in any existing strided layer such as strided convolution. The smoothing factor can be adjusted by changing the blur kernel filter size, where a larger filter size results in increased blur.
Source: Making Convolutional Networks Shift-Invariant Again
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Image Classification | 3 | 16.67% |
| Fine-Grained Image Classification | 2 | 11.11% |
| General Classification | 2 | 11.11% |
| Speech Synthesis | 1 | 5.56% |
| Text-To-Speech Synthesis | 1 | 5.56% |
| Multi-Label Classification | 1 | 5.56% |
| Object Detection | 1 | 5.56% |
| Fine-Grained Visual Recognition | 1 | 5.56% |
| Image Retrieval | 1 | 5.56% |
Usage Over Time
Components
| Component | Type |
|
|---|---|---|
| 🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |
