PLEIADES: Building Temporal Kernels with Orthogonal Polynomials
This work addresses efficient event-based data processing for applications like gesture recognition and automotive detection, representing a novel method for a known bottleneck.
The authors tackled the problem of online spatiotemporal classification and detection with low latency by introducing PLEIADES, a neural network class using temporal convolution kernels from orthogonal polynomials, achieving state-of-the-art results on three event-based benchmarks with high accuracy and low resource usage.
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: 1) 99.59% accuracy with 192K parameters on the DVS128 hand gesture recognition dataset and 100% with a small additional output filter; 2) 99.58% test accuracy with 277K parameters on the AIS 2024 eye tracking challenge; and 3) 0.556 mAP with 576k parameters on the PROPHESEE 1 Megapixel Automotive Detection Dataset.