文献阅读：Pyramid Vision Transformer: A Versatile Backbone for Dense Prediction without Convolutions
- Abstract
- 1. Introduction
- 2. Related Work
-
- 2.1. Convolutional Backbones in Computer Vision
- 2.2. Dense Prediction Tasks 密集预测任务
- 2.3. Self-Attention and Transformer in Vision
- 3. Pyramid Vision Transformer (PVT)
-
- 3.1. Overall Architecture
- 3.2. Feature Pyramid for Transformer
- 3.3. Transformer Encoder