Stable Rank Normalization (SRN) is a weight-normalization scheme which minimizes the stable rank of a linear operator. It simultaneously controls the Lipschitz constant and the stable rank of a linear operator. Stable rank is a softer version of the rank operator and is defined as the squared ratio of the Frobenius norm to the spectral norm.
Source: Stable Rank Normalization for Improved Generalization in Neural Networks and GANsPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Novel View Synthesis | 2 | 6.90% |
Computational Efficiency | 2 | 6.90% |
Image Reconstruction | 2 | 6.90% |
3D Object Reconstruction | 1 | 3.45% |
3D Reconstruction | 1 | 3.45% |
Decoder | 1 | 3.45% |
Object Reconstruction | 1 | 3.45% |
Data Visualization | 1 | 3.45% |
Machine Translation | 1 | 3.45% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |