论文标题
SWIN-POSE：基于Swin Transformer的人姿势估计
Swin-Pose: Swin Transformer Based Human Pose Estimation
论文作者
论文摘要
卷积神经网络（CNN）已在许多计算机视觉任务中广泛使用。但是，CNN具有固定的接收场，并且缺乏远程感知的能力，这对于人类的姿势估计至关重要。由于它有能力捕获像素之间的远程依赖性，因此最近对计算机视觉应用程序采用了变压器体系结构，并被证明是高效的体系结构。我们有兴趣探索其在人类姿势估计中的能力，因此提出了一个基于变压器结构的新型模型，并通过特征金字塔融合结构增强了。更具体地说，我们使用预训练的Swin变压器作为主链，并从输入图像中提取特征，我们利用特征金字塔结构从不同阶段提取特征图。通过将功能融合在一起，我们的模型可以预测关键点热图。我们研究的实验结果表明，与最新的基于CNN的模型相比，提出的基于变压器的模型可以实现更好的性能。
Convolutional neural networks (CNNs) have been widely utilized in many computer vision tasks. However, CNNs have a fixed reception field and lack the ability of long-range perception, which is crucial to human pose estimation. Due to its capability to capture long-range dependencies between pixels, transformer architecture has been adopted to computer vision applications recently and is proven to be a highly effective architecture. We are interested in exploring its capability in human pose estimation, and thus propose a novel model based on transformer architecture, enhanced with a feature pyramid fusion structure. More specifically, we use pre-trained Swin Transformer as our backbone and extract features from input images, we leverage a feature pyramid structure to extract feature maps from different stages. By fusing the features together, our model predicts the keypoint heatmap. The experiment results of our study have demonstrated that the proposed transformer-based model can achieve better performance compared to the state-of-the-art CNN-based models.
