EvoNorms are a set of normalization-activation layers that go beyond existing design patterns. Normalization and activation are unified into a single computation graph, its structure is evolved starting from low-level primitives. EvoNorms consist of two series: B series and S series. The B series are batch-dependent and were discovered by our method without any constraint. The S series work on individual samples, and were discovered by rejecting any batch-dependent operations.
Source: Evolving Normalization-Activation LayersPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Image Classification | 1 | 25.00% |
Image Generation | 1 | 25.00% |
Instance Segmentation | 1 | 25.00% |
Semantic Segmentation | 1 | 25.00% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |