Visualizing How Embeddings Generalize Article Swipe
Related Concepts
Computer science
Mathematics
Xiaotong Liu
,
Hong Xuan
,
Zeyu Zhang
,
Abby Stylianou
,
Robert Pless
·
YOU?
·
· 2019
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1909.07464
· OA: W2974155053
YOU?
·
· 2019
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.1909.07464
· OA: W2974155053
Deep metric learning is often used to learn an embedding function that captures the semantic differences within a dataset. A key factor in many problem domains is how this embedding generalizes to new classes of data. In observing many triplet selection strategies for Metric Learning, we find that the best performance consistently arises from approaches that focus on a few, well selected triplets.We introduce visualization tools to illustrate how an embedding generalizes beyond measuring accuracy on validation data, and we illustrate the behavior of a range of triplet selection strategies.
Related Topics
Finding more related topics…