A Single Graph Convolution Is All You Need: Efficient Grayscale Image Classification

TL;DR

This paper introduces a lightweight, single graph convolutional layer model for efficient grayscale image classification, achieving lower latency and competitive accuracy in medical and SAR ATR applications.

Contribution

The paper proposes a novel approach using a single graph convolutional layer with a vectorized image view and FPGA acceleration for fast, accurate grayscale image classification.

Findings

Achieves up to 16x latency reduction on MSTAR dataset.

Maintains competitive accuracy with state-of-the-art models.

Demonstrates effectiveness in medical and SAR ATR image classification.

Abstract

Image classifiers for domain-specific tasks like Synthetic Aperture Radar Automatic Target Recognition (SAR ATR) and chest X-ray classification often rely on convolutional neural networks (CNNs). These networks, while powerful, experience high latency due to the number of operations they perform, which can be problematic in real-time applications. Many image classification models are designed to work with both RGB and grayscale datasets, but classifiers that operate solely on grayscale images are less common. Grayscale image classification has critical applications in fields such as medical imaging and SAR ATR. In response, we present a novel grayscale image classification approach using a vectorized view of images. By leveraging the lightweight nature of Multi-Layer Perceptrons (MLPs), we treat images as vectors, simplifying the problem to grayscale image classification. Our approach incorporates a single graph convolutional layer in a batch-wise manner, enhancing accuracy and reducing performance variance. Additionally, we develop a customized accelerator on FPGA for our model, incorporating several optimizations to improve performance. Experimental results on benchmark grayscale image datasets demonstrate the effectiveness of our approach, achieving significantly lower latency (up to $16\times$ less on MSTAR) and competitive or superior performance compared to state-of-the-art models for SAR ATR and medical image classification.