US Patent 11188799 Semantic segmentation with soft cross-entropy loss
Patent 11188799 was granted and assigned to Sony on November, 2021 by the United States Patent and Trademark Office.
All edits
A system and method for semantic segmentation with a soft cross-entropy loss is provided. The system inputs a first color image to an input layer of a semantic segmentation network for a multi-class classification task. The semantic segmentation network generates, at an auxiliary stride, a first feature map as an output of an auxiliary layer of the semantic segmentation network based on the input first color image. The system extracts the generated first feature map from the auxiliary layer and computes a probability map as a set of soft labels over a set of classes of the multi-class classification task, based on the extracted first feature map. The system further computes an auxiliary cross-entropy loss between the computed probability map and a ground truth probability map for the auxiliary stride and trains the semantic segmentation network for the multi-class classification task based on the computed auxiliary cross-entropy loss.
US Patent 11188799 Semantic segmentation with soft cross-entropy loss
Find more entities like US Patent 11188799 Semantic segmentation with soft cross-entropy loss
