Knowledge Commons of Institute of Automation,CAS
MTLDesc: Looking Wider to Describe Better | |
Changwei Wang1,3; Rongtao Xu1,3; Yuyang Zhang1,3; Shibiao Xu2; Weiliang Meng1,3,4; Xiaopeng Zhang5 | |
2022-02 | |
会议名称 | 36th AAAI conference on Artificial Intelligence(AAAI2022) |
会议日期 | February 22-28, 2022 |
会议地点 | Virtual |
摘要 | Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context. In this work, we focus on making local descriptors “look wider to describe better” by learning local Descriptors with More Than just Local information (MTLDesc). Specifically, we resort to context augmentation and spatial attention mechanisms to make our MTLDesc obtain non-local awareness. First, Adaptive Global Context Augmented Module and Diverse Local Context Augmented Module are proposed to construct robust local descriptors with context information from global to local. Second, Consistent Attention Weighted Triplet Loss is designed to integrate spatial attention awareness into both optimization and matching stages of local descriptors learning. Third, Local Features Detection with Feature Pyramid is given to obtain more stable and accurate keypoints localization. With the above innovations, the performance of our MTLDesc significantly surpasses the prior state-of-the-art local descriptors on HPatches, Aachen Day-Night localization and InLoc indoor localization benchmarks. |
收录类别 | EI |
语种 | 英语 |
七大方向——子方向分类 | 模式识别基础 |
文献类型 | 会议论文 |
条目标识符 | http://ir.ia.ac.cn/handle/173211/47433 |
专题 | 多模态人工智能系统全国重点实验室_三维可视计算 |
通讯作者 | Shibiao Xu; Weiliang Meng |
作者单位 | 1.NLPR, Institute of Automation, Chinese Academy of Sciences 2.School of Artificial Intelligence, Beijing University of Posts and Telecommunications 3.School of Artificial Intelligence, University of Chinese Academy of Sciences 4.Zhejiang Lab 5.School of Automation and Electrical Engineering, University of Science and Technology Beijing |
第一作者单位 | 模式识别国家重点实验室 |
通讯作者单位 | 模式识别国家重点实验室 |
推荐引用方式 GB/T 7714 | Changwei Wang,Rongtao Xu,Yuyang Zhang,et al. MTLDesc: Looking Wider to Describe Better[C],2022. |
条目包含的文件 | 下载所有文件 | |||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
camera ready aaai202(7473KB) | 会议论文 | 开放获取 | CC BY-NC-SA | 浏览 下载 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论