Open Set Cross-Domain Hyperspectral Image Classification Based on Critical Reflective Learning Network

Limited by the lack of supervisory information of unknown classes, existing open set cross-domain hyperspectral image (HSI) classification methods often rely on threshold-based methods when identifying unknown classes, and are difficult to adapt to the complex inter-class variability between unknown and known classes in HSI. To solve this problem, this paper proposes a critical-reflective learning network (CRLN) based on teacher-student network, which obtains the unknown classes probability from the prediction of the closed set classifier (teacher network) and provides supervisory information for the open set classifier (student network). Specifically, first, the teacher network is trained with source domain data, and the unknown class probability predictions of the teacher network are obtained by quantifying the uncertainty of the network predictions. Second, the student network learns the complex boundary relationship between known and unknown classes based on the output of the teacher network to achieve accurate recognition of unknown classes. Furthermore, considering the credibility of the teacher network, a critical-reflective learning mechanism is proposed to allow the student network to reflect on the erroneous experiences of the teacher network, thus alleviating the performance damage caused by this potentially erroneous knowledge. Finally, the class alignment-separation module is proposed, which uses contrastive learning to promote the separation of known and unknown classes in the feature space, so as to reduce the risk of negative transfer induced by the confusion of the two types of features during cross-domain distribution adaptation. Experiments on three datasets show that the proposed method achieves state-of-the-art performance in the open set cross-domain HSI classification task.