The official repository for CosPGD: a unified white-box adversarial attack for pixel-wise prediction tasks.

Deep Convolutional Encoder-Decoder Architecture implemented along with max-pooling indices for pixel-wise semantic segmentation using CamVid dataset.

This study presents the first comprehensive review of large-scale, pixel-wise crop mapping methods. It integrates novel systematic experiments that evaluate the classification performance of entire workflows and assess their spatial, temporal, and sensor transferability across five diverse agricultural sites in the U.S. and Serbia.