Research publications.
Written by Minghui Chen
A novel federated model soup method that optimizes the trade-off between local and global performance through selective interpolation of model parameters, alleviating overfitting and seeking flat minima for improved generalization.
A novel data augmentation method that generates diverse on-manifold samples through multi-source vicinal transfer to improve model robustness against image corruptions.
The first comprehensive study establishing five ReID benchmarks for learning corruption invariant representations, providing insights on robustness of transformer vs CNN models and cross-dataset generalization.