Visformer, or Vision-friendly Transformer, is an architecture that combines Transformer-based architectural features with those from convolutional neural network architectures. Visformer adopts the stage-wise design for higher base performance. But self-attentions are only utilized in the last two stages, considering that self-attention in the high-resolution stage is relatively inefficient even when the FLOPs are balanced. Visformer employs bottleneck blocks in the first stage and utilizes group 3 × 3 convolutions in bottleneck blocks inspired by ResNeXt. It also introduces BatchNorm to patch embedding modules as in CNNs.
Source: Visformer: The Vision-friendly TransformerPaper | Code | Results | Date | Stars |
---|