对比学习结合DenseNet的高光谱图像开放集分类

打开文本图片集

关键词：高光谱图像；开放集;DenseNet;对比学习；困难样本挖掘中图分类号：TP751;TP181 文献标识码：Adoi：10.37188/OPE.20253323.3737 CSTR：32169.14.OPE.20253323.3737

Abstract：Hyperspectral image classification typically assumes that the training and test data share identical categories and that no unknown classes appear in the test set. However，this assumption is rarely satisfied in practical applications.Inaddition，thesubtle inter-classdiferences inherent in hyperspectraldataoften lead to overlapping feature distributions and consequent decision boundary ambiguity. To address these issues，anopen-set classification method for hyperspectral images is proposed that integrates contrastive learning with DenseNet. First，a spectral feature extraction module is employed to obtain the original spectral features，and multi-level feature interaction is realized through DenseNet.A transition module is further applied to compress spectral channels，thereby yielding clearer class boundary distributions. Second，the extracted spectral features are mapped to a spatial feature extraction module to obtain spatial-domain representations，where ResNet is adopted to capture local spatial structural information and enhance spatial perception. Subsequently，contrastive learning is introduced to reinforce intra-class compactness and inter-class separability，and is combined with a hard-sample mining mechanism to optimize ambiguous boundary features and improve the model's discriminative capability for boundary-region samples. Experiments conducted on the Houston 2Ol3，Pavia University，and WHU Hi-LongKou datasets demonstrate that the proposed method achieves superior ground-cover clasification performance on unknown categories，with accuracies of 68.81% ， 69.24% ，and 59.26% ，respectively. Meanwhile，overall accuracies of 89.49% ， 95.06% ，and 95.03% are obtained，indicating that the recognition of unknown categories is effectively enhanced while maintaining high classification accuracy for known categories.

Key words： hyperspectral image; open-set; DenseNet； contrastive learning； hard samples mining

1引言

高光谱图像（HyperspectralImage，HSI）能够在空间和光谱维度上提供丰富信息，因此广泛应用于精细地物分类[1]、环境监测[2]和军事侦察[3]等领域。（剩余19445字）