Similarity Learning lacks a framework. So we built one

Re:Similarity Learning lacks a framework. So we built one by usgroup on Wednesday July 13, 2022 @02:58PM (#32087262)

I’d be surprised if it’d be useful for something like cars or soccer players, or really anything that may not have a continuous mapping. I guess more generally whenever the underlying “true” similarity function is not differentiable — categorical data springs to mind (cars, football players…).

I could see it making sense for complex unstructured data — Qdrant seems to point in that direction.

[ Parent | on HN ]

Re:Similarity Learning lacks a framework. So we built one by monatis on Wednesday July 13, 2022 @03:25PM (#32087623)

Some loss functions such as ArcFace loss and CosFace loss enforce the encoder model to organize their latent space in such a way that categories are placed with an angular margin from one another. Thus the model implicitly learns a continuous distance function.

Fun fact, one of the examples in Quaterion is for similar cars search.

If you find this topic and want to discover more, we collected a bunch of resources that might be helpful. https://github.com/qdrant/awesome-metric-learning

[ Parent | on HN ]