# Polar-wise Binary Event Volume

This work adapts modern binary neural networks (BNNs) to event-camera data, introduces the Polar-wise Binary Event Volume (PBEV) binary representation and binarizes the network input layer, and shows that with knowledge distillation and RGB cross-modal pretraining BNNs match or exceed full-precision ResNet-18 on N-Caltech101 and N-ImageNet-mini classification, with a best result of 90.58% at fewer operations.

This work adapts modern binary neural networks (BNNs) to event-camera data, introduces the Polar-wise Binary Event Volume (PBEV) binary representation and binarizes the network input layer, and shows that with knowledge distillation and RGB cross-modal pretraining BNNs match or exceed full-precision ResNet-18 on N-Caltech101 and N-ImageNet-mini classification, with a best result of 90.58% at fewer operations.