HYPER-SNN: Towards Energy-efficient Quantized Deep Spiking Neural Networks for Hyperspectral Image Classification
This work addresses energy efficiency for hyperspectral image processing, which is crucial for resource-constrained applications like remote sensing, though it is incremental as it adapts existing SNN and quantization techniques to a specific domain.
The paper tackles the high energy cost of 3-D CNNs for hyperspectral image classification by proposing HYPER-SNN, a quantized deep spiking neural network that achieves similar accuracy to state-of-the-art methods with 560.6 times less compute energy than full-precision CNNs and 44.8 times less than quantized CNNs.
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.