Methods › Computer Vision › Backbone Architectures
Backbone Architectures
Transformers are a type of neural network architecture that have several properties that make them effective for modeling data with long-range dependencies. They generally feature a combination of multi-headed attention mechanisms, residual connections, layer normalization, feedforward connections, and positional embeddings.
Methods
All 10 methods in this collection, most-tagged first. Year is the archive's introduced_year; the archive stores 2000 when it has none, shown here as “–”. Papers counts distinct papers the archive tags with the method. Click a heading to sort.
| ConvNeXt | – | 165 |
| Deep Sets | – | 35 |
| Spatial Broadcast Decoder | – | 14 |
| TNT Transformer in Transformer | – | 12 |
| FFF Fast Feedforward Networks | – | 6 |
| 2D DWT 2D Discrete Wavelet Transform | – | 4 |
| CBNet Composite Backbone Network | – | 3 |
| RDNet | – | 3 |
| M-S structure Motion-Separable backbone structure | – | 1 |
| PoAPL Polar Angle Prediction Layer | – | 1 |