arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1909.07464cs.LGstat.ML
收藏

可视化嵌入如何泛化

Visualizing How Embeddings Generalize

The George Washington University(乔治华盛顿大学)

Xiaotong Liu, Hong Xuan, Zeyu Zhang, Abby Stylianou, Robert Pless

摘要:

深度度量学习通常用于学习嵌入函数,该函数捕获数据集中的语义差异。许多问题领域的一个关键因素是这种嵌入如何推广到新的数据类别。在观察度量学习的许多三元组选择策略时,我们发现最佳性能始终来自专注于少数精心选择的三元组的方法。我们引入可视化工具来说明嵌入如何超越验证数据的测量准确性,并说明一系列三元组选择策略的行为。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑