Ensembles of Compact, Region-specific & Regularized Spiking Neural Networks for Scalable Place Recognition
This addresses scalability for robotics applications using energy-efficient spiking neural networks, though it is incremental as it builds on existing SNN methods.
The paper tackles the scalability challenge of spiking neural networks for place recognition by introducing a modular ensemble approach with compact, region-specific networks and a regularization method to remove hyperactive neurons. It outperforms a previous SNN system on small datasets, maintains performance on datasets 27 times larger, and performs competitively with conventional localization systems like NetVLAD.
Spiking neural networks have significant potential utility in robotics due to their high energy efficiency on specialized hardware, but proof-of-concept implementations have not yet typically achieved competitive performance or capability with conventional approaches. In this paper, we tackle one of the key practical challenges of scalability by introducing a novel modular ensemble network approach, where compact, localized spiking networks each learn and are solely responsible for recognizing places in a local region of the environment only. This modular approach creates a highly scalable system. However, it comes with a high-performance cost where a lack of global regularization at deployment time leads to hyperactive neurons that erroneously respond to places outside their learned region. Our second contribution introduces a regularization approach that detects and removes these problematic hyperactive neurons during the initial environmental learning phase. We evaluate this new scalable modular system on benchmark localization datasets Nordland and Oxford RobotCar, with comparisons to standard techniques NetVLAD, DenseVLAD, and SAD, and a previous spiking neural network system. Our system substantially outperforms the previous SNN system on its small dataset, but also maintains performance on 27 times larger benchmark datasets where the operation of the previous system is computationally infeasible, and performs competitively with the conventional localization systems.