Classification of hyperspectral images via improved cycle‐MLP

Abstract

Pixel-wise classification of hyperspectral image (HSI) is a hot spot in the field of remote sensing. The classification of HSI requires the model to be more sensitive to dense features, which is quite different from the modelling requirements of traditional image classification tasks. Cycle-Multilayer Perceptron (MLP) has achieved satisfactory results in dense feature prediction tasks because it is an expert in extracting high-resolution features. In order to obtain a more stable receptive field and enhance the effect of feature extraction in multiple directions, we propose an MLP-like model called DriftNet for HSI classification inspired by Cycle-MLP and deformable convolution. Besides, the proposed DriftNet uses a unique ladder-like fully connected structure to achieve progressive activation of neurons and facilitates the fusion of spatial and spectral information, thereby obtaining more sensitive location information for better classification results. Experimental results on three public hyperspectral datasets demonstrate the effectiveness and generalisation of DriftNet. K E Y W O R D S cycleMLP, classification of hyperspectral image, deep learning, driftFCThis is an open access article under the terms of the Creative Commons Attribution-NonCommercial License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited and is not used for commercial purposes.

An Adaptive Weighted Method for Remote Sensing Image Retrieval with Noisy Labels

“…As a representative neural network structure, multilayer perceptron (MLP) is widely used in remote sensing tasks such as remote sensing image classification [32][33][34], object detection [35] and change detection [36,37]. The MLP can have multiple hidden layers between the input and output layers, but the simplest MLP has only one hidden layer.…”

S$^{2}$DCN: Spectral–Spatial Difference Convolution Network for Hyperspectral Image Classification

“…CNN-based networks excel at modeling local information in the spectral and spatial domains and representing intricate nonlinear features [32], [33]. MLP-based models boast superior flexibility and universality, making them particularly apt for managing the inherent dense features of HSI data [34], [35]. Models rooted in the ViT paradigm demonstrate a distinct edge in addressing long-term dependencies in HSI data, capturing global features effectively [36], [37].…”

LiteCCLKNet: A lightweight criss‐cross large kernel convolutional neural network for hyperspectral image classification

“…However, the local receptive field settings also make them less robust to local variable features in HSIs. In contrast, ViT-based [30] and MLP-based [31] models manage global contextual information through self-attention mechanisms and fully connected mappings over feature sequences respectively. This advantage helps them to mitigate the adverse effects of local variable features, but also leads to complex models with massive parameters.…”

“…To mitigate information redundancy [50] and Hughes phenomenon [51] due to the high spectral correlation of HSI data, we use the principal component analysis method to reduce the spectral dimensionality and retain the first eight principal components in the sample extraction stage. The local neighbourhood sampling is then performed with a patch size of 15 � 15, which is a common configuration in previous work [2,30,31]. We used a consistent training set construction approach with equal random sampling of 10, 50, and 1000 samples per class for the Indian Pines (1.5%), Salinas (1.5%), and Xiongan (0.5%) datasets respectively.…”