Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
Wenhai Wang, Enze Xie, Xiang Li et al.
2021 · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · 4,656 citations
Although convolutional neural networks (CNNs) have achieved great success in computer vision, this work investigates a simpler, convolution-free backbone network use-fid for many dense prediction tasks. Unlike the recently-proposed Vision Transformer (ViT) that was designed for image classification specifically, we introduce the Pyramid Vision Transformer (PVT), which overcomes the difficulties of porting Transformer to various dense prediction tasks. PVT has several merits compared to current state of the arts. (1) Different from ViT that typically yields low-resolution outputs and incurs hi…
Explore this paper's citation graph on Constellation.