PVT v2: Improved baselines with Pyramid Vision Transformer

Transformer recently has presented encouraging progress in computer vision. In this work, we present new baselines by improving the original Pyramid Vision (PVT v1) adding three designs, including (1) linear complexity attention layer, (2) overlapping patch embedding, and (3) convolutional feed-forward network. With these modifications, PVT v2 reduces computational of v1 to achieves significant improvements on fundamental vision tasks such as classification, detection, segmentation. Notably, proposed comparable or better performances than recent works Swin Transformer. We hope work will facilitate state-of-the-art researches Code is available at https://github.com/whai362/PVT.