arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2202.00770cs.CV
收藏

低端设备与Transformers的本地功能匹配

Local Feature Matching with Transformers for low-end devices

Kyrylo Kolodiazhnyi

摘要:

LoFTR arXiv:2104.00680是一种有效的深度学习方法,用于在图像对上找到适当的局部特征匹配。本文报告了这种方法的优化工作在设备上具有低的计算性能和有限的内存。最初的LoFTR方法基于ResNet arXiv:1512.03385头和两个基于线性Transformer arXiv:2006.04768架构的模块。在所提出的工作中,只留下粗匹配块,参数的数量显着减少,并使用知识蒸馏技术训练网络。比较表明,这种方法允许获得适当的特征检测精度的学生模型相比,教师模型在粗匹配块,尽管模型大小的显着减少。此外,本文还展示了使模型与NVIDIA TensorRT运行时兼容所需的其他步骤,并展示了一种优化低端GPU训练方法的方法。

英文摘要:

LoFTR arXiv:2104.00680 is an efficient deep learning method for finding appropriate local feature matches on image pairs. This paper reports on the optimization of this method to work on devices with low computational performance and limited memory. The original LoFTR approach is based on a ResNet arXiv:1512.03385 head and two modules based on Linear Transformer arXiv:2006.04768 architecture. In the presented work, only the coarse-matching block was left, the number of parameters was significantly reduced, and the network was trained using a knowledge distillation technique. The comparison showed that this approach allows to obtain an appropriate feature detection accuracy for the student model compared to the teacher model in the coarse matching block, despite the significant reduction of model size. Also, the paper shows additional steps required to make model compatible with NVIDIA TensorRT runtime, and shows an approach to optimize training method for low-end GPUs.

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。

↑