Experimental results on three widely used HSI datasets show that our proposed ASLPA method performs better than the state-of-the-art label-cleaning methods.

CORRECTING NOISY LABELS DURING THE CLASSIFICATION OF HYPERSPECTRAL IMAGES ; Qiliang Wei, Peng Fu, Nanjing University of Science and Technology, China ; Session:.

Training datasets for deep models inevitably contain noisy labels, such labels can seriously impair the performance of deep models. Empirically, all labels ...

Aiming at the classification of hyperspectral images with noise labels. •. Focus on the enhancing the classification accuracy of meta-weight-net methods. •. A ...

In this section, we formalize the foundational definitions and setup of the noisy label hyperspectral image classification problem. A hyperspectral image cube ...

Under this framework, we propose a novel label-correction method named adaptive selective loss propagation algorithm (ASLPA). Firstly, the spectral–spatial ...

In this paper, we overcome this challenge by using synthetic samples and proposing semi-supervised variational generative adversarial networks (GANs). In ...

In order to perform HSI classification with noisy labels, a robust weakly supervised feature learning (WSFL) architecture combined with multi-model attention is ...

Experimental studies show that the RLPA can reduce the level of noisy label and demonstrates the advantages of the proposed method over four major ...

Apply Classification methods such as SVM, MLR, KNN, KOMP on the corrected training labels. Fig. 1 illustrates the overall framework of the proposed MMS-based ...