IEEE

Human-Annotated Label Noise and Their Impact on ConvNets for Remote Sensing Image Scene Classification

Abstract: Human-labeled training datasets are essential for convolutional neural networks (ConvNets) in satellite image scene classification. Annotation errors are unavoidable due to the complexity of ...
IEEE

Spectral Structure-Aware Initialization and Probability-Consistent Self-Training for Cross-Scene Hyperspectral Image Classification

Abstract: Cross-scene classification of hyperspectral images (HSIs) aims to classify target domain (TD) data using only labeled source domain (SD) data and unlabeled TD data during training. However, ...