Vision Transformers for Dense Prediction

Understand

We introduce dense vision transformers, an architecture that leverages vision transformers in place of convolutional networks as a backbone for dense prediction tasks.

• We assemble tokens from various stages of the vision transformer into image-like representations at various resolutions and progressively combine them into full-resolution predictions using a convolutional decoder.
• The transformer backbone processes representations at a constant and relatively high resolution and has a global receptive field at every stage.
• These properties allow the dense vision transformer to provide finer-grained and more globally coherent predictions when compared to fully-convolutional networks.