Data-Efficient Spectral Classification of Hyperspectral Data Using MiniROCKET and HDC-MiniROCKET
This work addresses data efficiency for spectral classification, which is important for applications like agriculture and remote sensing, but it is incremental as it adapts existing methods to a specific bottleneck.
The paper tackles the problem of spectral classification in hyperspectral images with limited training data, showing that MiniROCKET and HDC-MiniROCKET outperform the state-of-the-art 1D-Justo-LiuNet in data-scarce scenarios, achieving competitive performance with concrete accuracy improvements.
The classification of pixel spectra of hyperspectral images, i.e. spectral classification, is used in many fields ranging from agricultural, over medical to remote sensing applications and is currently also expanding to areas such as autonomous driving. Even though for full hyperspectral images the best-performing methods exploit spatial-spectral information, performing classification solely on spectral information has its own advantages, e.g. smaller model size and thus less data required for training. Moreover, spectral information is complementary to spatial information and improvements on either part can be used to improve spatial-spectral approaches in the future. Recently, 1D-Justo-LiuNet was proposed as a particularly efficient model with very few parameters, which currently defines the state of the art in spectral classification. However, we show that with limited training data the model performance deteriorates. Therefore, we investigate MiniROCKET and HDC-MiniROCKET for spectral classification to mitigate that problem. The model extracts well-engineered features without trainable parameters in the feature extraction part and is therefore less vulnerable to limited training data. We show that even though MiniROCKET has more parameters it outperforms 1D-Justo-LiuNet in limited data scenarios and is mostly on par with it in the general case