期刊
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
卷 -, 期 -, 页码 4433-4442出版社
IEEE COMPUTER SOC
DOI: 10.1109/CVPR52688.2022.00440
关键词
-
This paper presents a novel contour-based method called E2EC for high-quality instance segmentation. By using a learnable contour initialization and a dynamic matching loss function, E2EC improves the accuracy and boundary detail quality of the segmentation. Experimental results demonstrate that E2EC achieves state-of-the-art performance on multiple datasets and is efficient for real-time applications.
Contour-based instance segmentation methods have developed rapidly recently but feature rough and hand-crafted front-end contour initialization, which restricts the model performance, and an empirical and fixed backend predicted-label vertex pairing, which contributes to the learning difficulty. In this paper, we introduce a novel contour-based method, named E2EC, for high-quality instance segmentation. Firstly, E2EC applies a novel learnable contour initialization architecture instead of hand-crafted contour initialization. This consists of a contour initialization module for constructing more explicit learning goals and a global contour deformation module for taking advantage of all of the vertices' features better. Secondly, we propose a novel label sampling scheme, named multi-direction alignment, to reduce the learning difficulty. Thirdly, to improve the quality of the boundary details, we dynamically match the most appropriate predicted-ground truth vertex pairs and propose the corresponding loss function named dynamic matching loss. The experiments showed that E2EC can achieve a state-of-the-art performance on the KITTI INStance (KINS) dataset, the Semantic Boundaries Dataset (SBD), the Cityscapes and the COCO dataset. E2EC is also efficient for use in real-time applications, with an inference speed of 36 fps for 512x512 images on an NVIDIA A6000 GPU. Code will be released at httpps://github.com/zhang-tao-whu/e2ec.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据