Removing the Compute Bottleneck for Event-based Visual Place Recognition with Spiking Neural Networks

arXiv:2610.16022 · cs.CV · Submitted 2026-10-12 · Read on arXiv

cs.CV

Submitted: 2026-10-12

Updated: 2026-10-12

Comments: 8 pages, 6 figures, under review

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Spiking neural networks — 1× in this paper · explained in 2 episodes

Sources

• Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding
• Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognition
• A Survey of Neuromorphic Computing and Neural Networks in Hardware
• A Survey on Efficient Training of Transformers

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models