Search Results for author:
Found 2 papers, 2 papers with code
Human-in-the-loop: Towards Label Embeddings for Measuring Classification Difficulty
The main idea of this work is to drop the assumption of a ground truth label and instead embed the annotations into a multidimensional space.
Going Beyond One-Hot Encoding in Classification: Can Human Uncertainty Improve Model Performance?
Technological and computational advances continuously drive forward the broad field of deep learning.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
