Structured Pruning for Efficient Visual Place Recognition
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Adversarial Attacks and Detection in Visual Place Recognition for Safer Robot Navigation
Place Recognition: A Comprehensive Review, Current Challenges and Future Directions
Geolocating Earth Imagery from ISS: Integrating Machine Learning with Astronaut Photography for Enhanced Geographic Mapping
Visual Re-Ranking with Non-Visual Side Information
Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition
To Match or Not to Match: Revisiting Image Matching for Reliable Visual Place Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.