.png){kind=icon}
返回
OpenInst: A simple query-based method for open-world instance segmentation
.png){kind=icon}
OA
AI
DOI：10.1016/j.patcog.2024.110570.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Open-world instance segmentation has recently gained significant popularity due to its importance in many real-world applications, such as autonomous driving, robot perception, and remote sensing. However, previous methods have either produced unsatisfactory results or relied on complex systems and paradigms. We wonder if there is a simple way to obtain state-of-the-art results. Fortunately, we have identified two observations that help us achieve the best of both worlds: (1) query-based methods demonstrate superiority over dense proposal-based methods in open-world instance segmentation, and (2) learning localization cues is sufficient for open-world instance segmentation. Based on these observations, we propose a simple query-based method named OpenInst for open-world instance segmentation. OpenInst leverages advanced query-based methods like QueryInst and focuses on learning localization cues. Notably, OpenInst is an extremely simple and straightforward framework without any auxiliary modules or post-processing, yet achieves state-of-the-art results on multiple benchmarks. Specifically, in the COCO -> UVO scenario, OpenInst achieves a mask Average Recall (AR) of 53.3, outperforming the previous best methods by 2.0 AR with a simpler structure. We hope that OpenInst can serve as a solid baseline for future research in this area. The source codes are available at https://github.com/hustvl/OpenInst.
Keyword:
Open-world instance segmentation
Object localization network
Query-based detector
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
7.6
论文数:
1.4W
被引数:
4.9W
机构
暂无机构信息
引用论文
Hierarchical objectness network for region proposal generation and object detection.png)
PATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏 没有更多内容
没有更多内容