arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.11366cs.CV
收藏

基于知识图谱嵌入的对比目标检测

Contrastive Object Detection Using Knowledge Graph Embeddings

Robert Bosch GmbH(罗伯特·博世有限公司);University of Freiburg(弗赖堡大学)

Christopher Lang, Alexander Braun, Abhinav Valada

摘要:

对象识别在很大程度上被视为一个单一的热点问题,它将类视为离散和不相关的。每个图像区域必须被分配给一组对象中的一个成员,包括背景类,而不管对象类型中的任何相似性。在这项工作中,我们比较了错误统计的类嵌入从一个热的方法与语义结构化的嵌入从自然语言处理或知识图谱,广泛应用于开放世界的目标检测。多个知识嵌入以及距离度量的广泛实验结果表明,基于知识的类表示导致更多的语义接地错误分类,同时表现在具有挑战性的COCO和Cityscapes目标检测基准相比,一个热的方法。我们将我们的发现推广到多个目标检测架构,提出了一个知识嵌入式设计的关键点为基础的和基于变换的目标检测架构。

英文摘要:

Object recognition for the most part has been approached as a one-hot problem that treats classes to be discrete and unrelated. Each image region has to be assigned to one member of a set of objects, including a background class, disregarding any similarities in the object types. In this work, we compare the error statistics of the class embeddings learned from a one-hot approach with semantically structured embeddings from natural language processing or knowledge graphs that are widely applied in open world object detection. Extensive experimental results on multiple knowledge-embeddings as well as distance metrics indicate that knowledge-based class representations result in more semantically grounded misclassifications while performing on par compared to one-hot methods on the challenging COCO and Cityscapes object detection benchmarks. We generalize our findings to multiple object detection architectures by proposing a knowledge-embedded design for keypoint-based and transformer-based object detection architectures.

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。

↑