Self-supervised learning with deep clustering for target detection in hyperspectral images with insufficient spectral variation prior

Target detection in hyperspectral images (HSIs) mainly relies on the spectral information of the target prior. However, prior spectra with precise variation information are often hard to obtain, and the “different objects with the same spectrum” phenomena in complex environments make it difficult to detect the variational targets. To mitigate this problem, self-supervised learning (SSL) is introduced to mine the spectral variation in the HSIs to supplement the priors. The SSL-based detector, termed SSDCTD, is optimized with unlabeled spectra using an unsupervised pretext task and restricted with prior spectra in an end-to-end way. A deep clustering-based pretext task is designed, which utilizes the discriminative features among different substances to cluster the spectra in HSIs into several classes. Besides, we simultaneously optimize the detector to classify the priors into the target cluster. The combination of exploiting variational features from HSIs and supervision of target priors helps the proposed detector to make a great balance between target detectability (TD) and background suppressibility (BS). Experiments on four real datasets validate the superior performance of the proposed detector over several state-of-the-art detectors in multiple criteria.