Hybrid Convolutional Network Combining 3D Depthwise Separable Convolution and Receptive Field Control for Hyperspectral Image Classification

Abstract

Deep-learning-based methods have been widely used in hyperspectral image classification. In order to solve the problems of the excessive parameters and computational cost of 3D convolution, and loss of detailed information due to the excessive increase in the receptive field in pursuit of multi-scale features, this paper proposes a lightweight hybrid convolutional network called the 3D lightweight receptive control network (LRCNet). The proposed network consists of a 3D depthwise separable convolutional network and a receptive field control network. The 3D depthwise separable convolutional network uses the depthwise separable technique to capture the joint features of spatial and spectral dimensions while reducing the number of computational parameters. The receptive field control network ensures the extraction of hyperspectral image (HSI) details by controlling the convolution kernel. In order to verify the validity of the proposed method, we test the classification accuracy of the LRCNet based on three public datasets, which exceeds 99.50% The results show that compare with state-of-the-art methods, the proposed network has competitive classification performance.

Optimizing the YOLOv7-Tiny Model with Multiple Strategies for Citrus Fruit Yield Estimation in Complex Scenarios

“…The floating-point operation per second (FLOPS) is the calculation speed; the larger the value, the better the network performance. The current mainstream conventional convolution, group convolution, and depth-wise separable convolution (DWConv) methods all suffer from low FLOPS problems, which is mainly due to frequent access memory [27]. For floating-point of operations (FLOPs), the greater the number of computations, the smaller the value, which is generally used to measure the model complexity.…”

A Decompressed Spectral-Spatial Multiscale Semantic Feature Network for Hyperspectral Image Classification

“…Owning to the abundant spatial and spectral information, HSI plays an important role in many practical applications, such as urban planning, land-cover investigation, precision agriculture, military detection, and environmental monitoring [5][6][7][8][9]. In the last few decades, HSI classification has been one of the most popular research fields [10] and attracted multitudinous scholars to devote great efforts to improving classification accuracy [11][12][13][14][15].…”