Hyperspectral image (HSI) classification remains challenging because of its high spectral dimensionality, limited labeled samples, and spatial-spectral variability. We propose DuSR-Net, a ...

An example of an image classification problem is to identify a photograph of an animal as a "dog" or "cat" or "monkey." The two most common approaches for image classification are to use a standard ...

Researchers have developed MAPLE, a black-box adversarial defense framework that jointly purifies adversarial images and recalibrates the classifier's decision margins to withstand transferable ...