通过结构化剪枝优化视觉定位模型，显著降低内存与延迟。
Structured Pruning for Efficient Visual Place Recognition
- 针对特征嵌入空间和网络结构双重冗余，提出结构化剪枝方法。
- 内存减少21%，推理延迟降低16%，召回率损失小于1%。
- 适合部署在资源受限的边缘设备上运行实时视觉定位。
视觉位置识别（VPR）是机器人与设备实现全局重定位的基础，使系统能基于视觉输入识别此前访问过的位置，对大范围精准建图与定位至关重要。由于VPR需在嵌入式系统上实时运行，优化资源消耗极为关键。现有高效VPR方法虽采用固定描述符维度的卷积主干网络，但常导致嵌入空间与网络架构存在冗余。本文提出一种新型结构化剪枝方法，不仅精简常见VPR架构，还针对性地消除特征嵌入空间中的冗余。该双重优化显著提升系统效率，降低地图与模型内存占用，并减少特征提取与检索延迟。实验表明，该方法在多个模型上实现21%的内存缩减与16%的延迟下降，同时召回率@1下降不足1%。这一成果极大提升了边缘设备上实时应用的可行性。
原文摘要 · Abstract (English)
Visual Place Recognition (VPR) is fundamental for the global re-localization of robots and devices, enabling them to recognize previously visited locations based on visual inputs. This capability is crucial for maintaining accurate mapping and localization over large areas. Given that VPR methods need to operate in real-time on embedded systems, it is critical to optimize these systems for minimal resource consumption. While the most efficient VPR approaches employ standard convolutional backbones with fixed descriptor dimensions, these often lead to redundancy in the embedding space as well as in the network architecture. Our work introduces a novel structured pruning method, to not only streamline common VPR architectures but also to strategically remove redundancies within the feature embedding space. This dual focus significantly enhances the efficiency of the system, reducing both map and model memory requirements and decreasing feature extraction and retrieval latencies. Our approach has reduced memory usage and latency by 21% and 16%, respectively, across models, while minimally impacting recall@1 accuracy by less than 1%. This significant improvement enhances real-time applications on edge devices with negligible accuracy loss.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。