awesome-metric-learning VS pytorch-metric-learning

And, for resources on similarity learning at large, you may want to check out this annotated list: https://github.com/qdrant/awesome-metric-learning

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

The Metric Learning approach to data science problems is heavily underutilized. There are a lot of academic papers around it but much fewer practical guides and tutorials. So we decided that we could help people adopt metric learning by collecting related materials in one place. We are publishing a curated list of awesome practical metric learning tools, libraries, and materials - https://github.com/qdrant/awesome-metric-learning This collection aims to put together references to all required materials for building your application using Metric Learning. It is open-source, PR's are more than welcome!

Not a full featured framework, but pytorch-metric-learning has data loaders, lossess, etc. to facilitate similarity learning: https://github.com/KevinMusgrave/pytorch-metric-learning

Disclaimer: I've made some contributions to it.

You can use the triplet loss together with the Gaussian prior. It will be zero centered though and the clusters are not as separated when you use the triplet loss only.There are many alternative to the triplet loss, in case it needs to be a metric: https://github.com/KevinMusgrave/pytorch-metric-learning

This repo provides the tools and examples needed to build such a model: https://github.com/KevinMusgrave/pytorch-metric-learning