PLEIADES: Building Temporal Kernels with Orthogonal Polynomials

orthogonal polynomials spatiotemporal event-based convolutional neural networks object detection

⋅ NeurIPS ⋅ Project Page ⋅Slides ⋅Poster ⋅OpenReview

Abstract

We introduce a class of neural networks named PLEIADES (PoLynomial Expansion In Adaptive Distributed Event-based Systems), which contains temporal convolution kernels generated from orthogonal polynomial basis functions. We focus on interfacing these networks with event-based data to perform online spatiotemporal classification and detection with low latency.

By virtue of using structured temporal kernels and event-based data, we have the freedom to vary the sample rate of the data along with the discretization step-size of the network without additional finetuning. We experimented with three event-based benchmarks and obtained state-of-the-art results on all three by large margins with significantly smaller memory and compute costs.

We achieved:

99.59% accuracy with 192K parameters on the DVS128 hand gesture recognition dataset and 100% with a small additional output filter;
99.58% test accuracy with 277K parameters on the AIS 2024 eye tracking challenge; and
0.556 mAP with 576k parameters on the PROPHESEE 1 Megapixel Automotive Detection Dataset.