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 2312.09028cs.CV
收藏

面向视觉位置识别的低比特量化神经网络设计空间探索

Design Space Exploration of Low-Bit Quantized Neural Networks for Visual Place Recognition

University of Southampton(南安普顿大学);University of Essex(埃塞克斯大学);Queensland University of Technology(昆士兰科技大学)

Oliver Grainge, Michael Milford, Indu Bodala, Sarvapali D. Ramchurn, Shoaib Ehsan

AI总结:

针对当前视觉位置识别深度学习模型规模过大难以部署在低功耗边缘设备的问题,研究紧凑型卷积网络结合全精度与混合精度训练后量化的影响,兼顾性能与资源开销并给出设计建议。

摘要:

视觉位置识别(VPR)是视觉感知系统中实现全局重定位的关键任务,要求算法能够在光照、遮挡、外观及视角变化的条件下,准确识别出此前访问过的地点。在机器人系统与增强现实场景中,部署目标设备为电池供电的边缘设备,因此VPR方法的精度固然重要,内存占用与延迟同样关键。近期的新研究多将recall@1指标作为性能衡量标准,对资源利用率的关注十分有限,导致所提出的方法所使用的深度学习模型规模过大,无法部署在低功耗边缘设备上。我们假设这类大模型存在高度过参数化问题,可在保持高召回性能的同时进行优化,以满足低功耗嵌入式系统的约束。本研究探究了紧凑型卷积网络架构设计结合全精度与混合精度训练后量化对VPR性能的影响。值得注意的是,我们不仅通过recall@1分数衡量性能,还对内存占用与延迟进行了测算。我们梳理了设计选择对内存、延迟及召回分数的影响,并为存在此类资源限制的VPR系统提供了若干设计建议。

英文摘要:

Visual Place Recognition (VPR) is a critical task for performing global re-localization in visual perception systems. It requires the ability to accurately recognize a previously visited location under variations such as illumination, occlusion, appearance and viewpoint. In the case of robotic systems and augmented reality, the target devices for deployment are battery powered edge devices. Therefore whilst the accuracy of VPR methods is important so too is memory consumption and latency. Recently new works have focused on the recall@1 metric as a performance measure with limited focus on resource utilization. This has resulted in methods that use deep learning models too large to deploy on low powered edge devices. We hypothesize that these large models are highly over-parameterized and can be optimized to satisfy the constraints of a low powered embedded system whilst maintaining high recall performance. Our work studies the impact of compact convolutional network architecture design in combination with full-precision and mixed-precision post-training quantization on VPR performance. Importantly we not only measure performance via the recall@1 score but also measure memory consumption and latency. We characterize the design implications on memory, latency and recall scores and provide a number of design recommendations for VPR systems under these resource limitations.

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。

↑