Vision Transformers for Dense Prediction (ICCV 2021): State of the art accuracy on depth estimation and semantic segmentation (realtime >30 FPS)
Vision Transformers for Dense Prediction: (ICCV 2021) State of the art accuracy on depth estimation and semantic segmentation (realtime >30 FPS) 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. Our experiments show that this architecture yields substantial improvements on dense prediction tasks, especially when a large amount of training data is availa