arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2303.00364cs.CVcs.LG
收藏

经验报告:工程问题解决中探测任务的超分辨率

Lessons Learned Report: Super-Resolution for Detection Tasks in Engineering Problem-Solving

Martin Feder, Michal Horovitz, Assaf Chen, Raphael Linker, Ofer M. Shir

摘要:

我们描述了在低分辨率输入地图下,通过基于机器学习的超分辨率方法解决农业检测问题的经验教训。底层域是所谓的农业检测类问题,具体目标是学习零星输入地图的互补集合。虽然超分辨率算法被认为有能力增强通用摄影中各种有吸引力的功能,但我们认为它们必须满足某些要求,更重要的是,它们的结果并不一定保证工程检测问题解决的改进(不像ImageNet类数据集中所谓的美学/艺术超分辨率)。通过提出具体的数据驱动的案例研究,我们概述了一组限制和建议部署超分辨率算法的农业检测问题。另一个结论指出,超分辨率算法可以用于学习丢失的频谱通道,并且它们的使用可能会导致一些期望的副作用,例如通道的同步。

英文摘要:

We describe the lessons learned from targeting agricultural detection problem-solving, when subject to low resolution input maps, by means of Machine Learning-based super-resolution approaches. The underlying domain is the so-called agro-detection class of problems, and the specific objective is to learn a complementary ensemble of sporadic input maps. While super-resolution algorithms are branded with the capacity to enhance various attractive features in generic photography, we argue that they must meet certain requirements, and more importantly, that their outcome does not necessarily guarantee an improvement in engineering detection problem-solving (unlike so-called aesthetics/artistic super-resolution in ImageNet-like datasets). By presenting specific data-driven case studies, we outline a set of limitations and recommendations for deploying super-resolution algorithms for agro-detection problems. Another conclusion states that super-resolution algorithms can be used for learning missing spectral channels, and that their usage may result in some desired side-effects such as channels' synchronization.

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。

↑