Search Results for author:
Found 2 papers, 2 papers with code
Enriching Information and Preserving Semantic Consistency in Expanding Curvilinear Object Segmentation Datasets
To address these challenges, this paper introduces a novel approach for expanding curvilinear object segmentation datasets, focusing on enhancing the informativeness of generated data and the consistency between semantic maps and generated images.
Balanced joint maximum mean discrepancy for deep transfer learning
B-JMMD achieves the effect of balanced distribution adaptation for deep network architecture, and can be treated as an improved version of JMMD’s backpropagation algorithm.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
