arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.01877cs.CVcs.AIcs.LO
收藏

Faster-LTN:一种神经符号化的端到端目标检测架构

Faster-LTN: a neuro-symbolic, end-to-end object detection architecture

Politecnico di Torino(都灵理工大学);Dipartimento di Automatica e Informatica(自动化与信息系)

Francesco Manigrasso, Filomeno Davide Miro, Lia Morra, Fabrizio Lamberti

摘要:

检测图像中表示的对象之间的语义关系是图像判读中的基本挑战之一。诸如逻辑张量网络(LTN)的神经符号技术允许语义知识表示和推理与从神经网络的典型示例有效学习的能力的组合。我们在这里提出Faster-LTN,一个由卷积骨干和LTN组成的对象检测器。据我们所知,这是第一次尝试在端到端的培训环境中结合这两个框架。该架构通过优化将标记的示例与先验知识以逻辑公理的形式相结合的扎根理论来训练。实验比较表明,相对于传统的Faster R-CNN架构,它具有竞争力的性能。

英文摘要:

The detection of semantic relationships between objects represented in an image is one of the fundamental challenges in image interpretation. Neural-Symbolic techniques, such as Logic Tensor Networks (LTNs), allow the combination of semantic knowledge representation and reasoning with the ability to efficiently learn from examples typical of neural networks. We here propose Faster-LTN, an object detector composed of a convolutional backbone and an LTN. To the best of our knowledge, this is the first attempt to combine both frameworks in an end-to-end training setting. This architecture is trained by optimizing a grounded theory which combines labelled examples with prior knowledge, in the form of logical axioms. Experimental comparisons show competitive performance with respect to the traditional Faster R-CNN architecture.

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。

↑