CREST combines a conjoint learning rule, a multi-scale spatiotemporal event integrator, and a spatiotemporal IoU loss to improve accuracy and estimated energy efficiency of event-based object detection with spiking neural networks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
CREST: An Efficient Conjointly-trained Spike-driven Framework for Event-based Object Detection Exploiting Spatiotemporal Dynamics
CREST combines a conjoint learning rule, a multi-scale spatiotemporal event integrator, and a spatiotemporal IoU loss to improve accuracy and estimated energy efficiency of event-based object detection with spiking neural networks.