HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification

TL;DR

This paper introduces energy-efficient quantized deep spiking neural networks for hyperspectral image classification, achieving high accuracy with significantly reduced energy consumption compared to traditional CNNs.

Contribution

It proposes a novel SNN approach derived from CNNs, trained with quantization-aware gradient descent, for hyperspectral image classification with improved efficiency.

Findings

Achieved 98.68% accuracy on Indian Pines dataset.

Reduced energy consumption by over 500 times compared to full-precision CNNs.

Maintained high accuracy with only 6-bit weight quantization.

Abstract

Hyper spectral images (HSI) provide rich spectral and spatial information across a series of contiguous spectral bands. However, the accurate processing of the spectral and spatial correlation between the bands requires the use of energy-expensive 3-D Convolutional Neural Networks (CNNs). To address this challenge, we propose the use of Spiking Neural Networks (SNNs) that are generated from iso-architecture CNNs and trained with quantization-aware gradient descent to optimize their weights, membrane leak, and firing thresholds. During both training and inference, the analog pixel values of a HSI are directly applied to the input layer of the SNN without the need to convert to a spike-train. The reduced latency of our training technique combined with high activation sparsity yields significant improvements in computational efficiency. We evaluate our proposal using three HSI datasets on a 3-D and a 3-D/2-D hybrid convolutional architecture. We achieve overall accuracy, average accuracy, and kappa coefficient of 98.68%, 98.34%, and 98.20% respectively with 5 time steps (inference latency) and 6-bit weight quantization on the Indian Pines dataset. In particular, our models achieved accuracies similar to state-of-the-art (SOTA) with 560.6 and 44.8 times less compute energy on average over three HSI datasets than an iso-architecture full-precision and 6-bit quantized CNN, respectively.