论文标题
骨架提取的上下文注意网络
Context Attention Network for Skeleton Extraction
论文作者
论文摘要
骨架提取是一项旨在通过从给定的二进制或RGB图像中提取骨架来提供对象的简单表示的任务。近年来，已经制作了许多有吸引力的骨骼提取作品。但是据我们所知，关于如何利用对象二进制形状的上下文信息的研究很少。在本文中，我们提出了一个名为“上下文注意网络”（CANET）的基于注意力的模型，该模型将上下文提取模块集成在UNET体系结构中，并可以有效地提高网络提取骨骼像素的能力。同时，我们还使用一些新型技术，包括距离变换，重量局部损失，以在给定数据集上取得良好的结果。最后，没有模型集合，只有80％的训练图像，我们的方法在开发阶段获得了0.822 F1得分，在像素Skelneton竞赛的最后阶段，在排行榜上排名第一。
Skeleton extraction is a task focused on providing a simple representation of an object by extracting the skeleton from the given binary or RGB image. In recent years many attractive works in skeleton extraction have been made. But as far as we know, there is little research on how to utilize the context information in the binary shape of objects. In this paper, we propose an attention-based model called Context Attention Network (CANet), which integrates the context extraction module in a UNet architecture and can effectively improve the ability of network to extract the skeleton pixels. Meanwhile, we also use some novel techniques including distance transform, weight focal loss to achieve good results on the given dataset. Finally, without model ensemble and with only 80% of the training images, our method achieves 0.822 F1 score during the development phase and 0.8507 F1 score during the final phase of the Pixel SkelNetOn Competition, ranking 1st place on the leaderboard.
