T. Acharya

Mitigating Class Imbalance and False-Negative Supervision in Remote Sensing Semantic Segmentation Using Object-Centric Patch Sampling

Object-centric patch sampling, a model-independent strategy that anchors each training patch to the geometric centroid of an annotated object, is proposed, a model-independent strategy that improves training data quality at its source and integrates seamlessly into any deep learning pipeline without architectural modif...