IEEE Transactions on Geoscience and Remote Sensing · 2024 · 11 citations · 35 references
ComputingComputer ScienceComputer VisionFeature EngineeringMachine LearningDimensionality ReductionGraph-based LearningHyperspectral ImagingImage ClassificationImage Feature EngineeringRepresentation LearningContrastive LearningConvolutional Neural NetworksGraph Contrastive LearningGraph Convolutional NetworksHyperspectral Image ProcessingLearned Feature EmbeddingsLow-dimensional EmbeddingsMultilayer Perceptron
Due to the scarcity of prior information and the high complexity of spectral data, hyperspectral image (HSI) clustering presents a significant challenge. Although recent deep clustering methods have demonstrated remarkable performance, their intricate network structures and poor robustness hinder their practical application. To address this issue, we propose an efficient and lightweight spectral-spatial feature graph contrastive learning (S2GCL) framework for robust HSI clustering. Specifically, we have designed a novel spectral-spatial feature encoder that fully leverages the information in HSI by incorporating both spatial structure and spectral similarity matrices. To establish a lightweight model, we implement several effective designs: First, S2GCL eliminates the commonly used data augmentation and discriminator in GCL during the generation of positive embeddings. Second, we use a multilayer perceptron (MLP) to produce low-dimensional embeddings instead of relying on graph convolutional networks (GCNs). Third, negative embeddings are generated through row-shuffling, avoiding the use of neural networks. Finally, we propose a multiple boundary loss function to extract complementary information from spatial structures and neighboring nodes, while also constraining the interclass differences between positive and negative examples. We conducted extensive experiments on four publicly available datasets and compared S2GCL with state-of-the-art clustering methods. The results indicate that S2GCL achieves satisfactory performance. The code for S2GCL will be released at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/ahappyyang/S2GCL</uri>.
35
Graph Convolutional Networks for Hyperspectral Image Classification
Danfeng Hong, Lianru Gao, Jing Yao et al. · IEEE Transactions on Geoscience and Remote Sensing · 2020 · 1.6K citations · Full text
Graph Contrastive Learning with Adaptive Augmentation
Yanqiao Zhu, Yichen Xu, Feng Yu et al. · 2021 · 1K citations · Full text
Attributed Graph Clustering: A Deep Attentional Embedding Approach
Chun Wang, Shirui Pan, Ruiqi Hu et al. · 2019 · 536 citations · Full text
Structural Deep Clustering Network
2020 · 492 citations · Full text