Search Results for author:
Found 5 papers, 2 papers with code
Linear optimal transport subspaces for point set classification
Our approach employs the Linear Optimal Transport (LOT) transform to obtain a linear embedding of set-structured data.
Transport-based morphometry of nuclear structures of digital pathology images in cancers
We demonstrate the model is robust to different staining patterns and imaging protocols, and can be used to discover meaningful and interpretable information within and across datasets and cancer types.
A sliced-Wasserstein distance-based approach for out-of-class-distribution detection
These methods often require extensive training data, are computationally expensive, and are vulnerable to out-of-distribution samples, e. g., adversarial attacks.
End-to-End Signal Classification in Signed Cumulative Distribution Transform Space
This paper presents a new end-to-end signal classification method using the signed cumulative distribution transform (SCDT).
Invariance encoding in sliced-Wasserstein space for image classification with limited training data
However, they are known to underperform when training data are limited and thus require data augmentation strategies that render the method computationally expensive and not always effective.
