arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1711.11575cs.CV
收藏

目标检测的关系网络

Relation Networks for Object Detection

Microsoft Research Asia(微软亚洲研究院);Peking University(北京大学)

Han Hu, Jiayuan Gu, Zheng Zhang, Jifeng Dai, Yichen Wei

摘要:

尽管多年来人们一直认为对象之间的建模关系有助于对象识别,但没有证据表明这种想法在深度学习时代有效。所有最先进的目标检测系统仍然依赖于单独识别对象实例,而不利用它们在学习期间的关系。本文提出了一个对象关系模块。它通过一组对象的外观特征和几何形状之间的交互同时处理一组对象,从而允许对它们之间的关系进行建模。它是轻量级的和到位。它不需要额外的监督,并且易于嵌入现有网络。实验结果表明,该方法在改进现代目标检测流水线中的目标识别和重复去除步骤方面是有效的。它验证了在基于CNN的检测中建模对象关系的有效性。它产生了第一个完全端到端的物体检测器。

英文摘要:

Although it is well believed for years that modeling relations between objects would help object recognition, there has not been evidence that the idea is working in the deep learning era. All state-of-the-art object detection systems still rely on recognizing object instances individually, without exploiting their relations during learning. This work proposes an object relation module. It processes a set of objects simultaneously through interaction between their appearance feature and geometry, thus allowing modeling of their relations. It is lightweight and in-place. It does not require additional supervision and is easy to embed in existing networks. It is shown effective on improving object recognition and duplicate removal steps in the modern object detection pipeline. It verifies the efficacy of modeling object relations in CNN based detection. It gives rise to the first fully end-to-end object detector.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑