3-D-ANAS: 3-D Asymmetric Neural Architecture Search for Fast Hyperspectral Image Classification

• Published in: IEEE transactions on geoscience and remote sensing Vol. 60; pp. 1 - 19
• Main Authors: Zhang, Haokui, Gong, Chengrong, Bai, Yunpeng, Bai, Zongwen, Li, Ying
• Format: Journal Article
• Language: English
• Published: New York IEEE 2022; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Asymmetric network search; asymmetric search space; Asymmetry; Classification; Computer applications; Computer architecture; Computing costs; Data mining; Datasets; Decomposition; Deep learning; Feature extraction; Frameworks; hyperspectral image (HSI) classification; Hyperspectral imaging; Image classification; inference speed; Information processing; Land cover; Machine learning; Neural networks; patch-to-pixel framework; Physical properties; pixel-to-pixel framework; Pixels; Principal component analysis; Search algorithms; Sensors; Solid modeling; Spatial data; Task analysis
• ISSN: 0196-2892; 1558-0644
• DOI: 10.1109/TGRS.2021.3079123

Hyperspectral images (HSIs) provide abundant spectral and spatial information, playing an irreplaceable role in land-cover classification. Recently, based on deep learning (DL) technologies, an increasing number of HSI classification approaches have been proposed, which demonstrate promising performance. However, previous studies suffer from two major drawbacks: 1) the architecture of most DL models is manually designed, relies on specialized knowledge, and is relatively tedious. Moreover, in HSI classifications, datasets captured by different sensors have different physical properties. Correspondingly, different models need to be designed for different datasets, which further increases the workload of designing architectures and 2) the mainstream framework is a patch-to-pixel framework. The overlap regions of patches of adjacent pixels are calculated repeatedly, which increases computational cost and time cost. In addition, the classification accuracy is sensitive to the patch size, which is artificially set based on extensive investigation experiments. To overcome the issues mentioned above, we first propose a 3-D asymmetric neural network search algorithm and leverage it to automatically search for efficient architectures for HSI classifications. By analyzing the characteristics of HSIs, we specifically build a 3-D asymmetric decomposition search space, where spectral and spatial information is processed with different decomposition convolutions. Furthermore, we propose a new fast classification framework, i.e., pixel-to-pixel classification framework, which has no repetitive operations and reduces the overall cost. Experiments on three public HSI datasets captured by different sensors demonstrate the networks designed by our 3-D asymmetric neural architecture search (3-D-ANAS) achieve competitive performance compared to several state-of-the-art methods, while having a much faster inference speed. Code is available at: https://github.com/hkzhang91/3D-ANAS .