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.
@article{arxiv.1909.07464,
title = {Visualizing How Embeddings Generalize},
author = {Xiaotong Liu and Hong Xuan and Zeyu Zhang and Abby Stylianou and Robert Pless},
journal= {arXiv preprint arXiv:1909.07464},
year = {2019}
}
Comments
8 pages,4 figures, published in ICML workshop:Understanding and Improving Generalization in Deep Learning