Visualizing How Embeddings Generalize

Abstract

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.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyliu2019visualizing

Related papers

• Sharing Matters For Generalization In Deep Metric Learning (2020)8.35
• Generalization In Metric Learning: Should The Embedding Layer Be The Embedding Layer? (2018)8.60
• Revisiting Training Strategies And Generalization Performance In Deep Metric Learning (2020)5.08
• Improved Embeddings With Easy Positive Triplet Mining (2019)15.06
• Visual Explanation For Deep Metric Learning (2019)14.36
• Divide And Conquer The Embedding Space For Metric Learning (2019)14.39
• Deep Metric Learning Assisted By Intra-variance In A Semi-supervised View Of Learning (2023)5.24
• Deep Randomized Ensembles For Metric Learning (2018)13.97