Similarity Learning lacks a framework. So we built one

• finetuner

  36 1,424 5.5 Python

  :dart: Task-oriented embedding tuning for BERT, CLIP, etc.

  

• pytorch-metric-learning

  3 5,764 7.9 Python

  The easiest way to use deep metric learning in your application. Modular, flexible, and extensible. Written in PyTorch.

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.

• InfluxDB

  www.influxdata.com sponsored

  Power Real-Time Data Analytics at Scale. Get real-time insights from all types of time series data with InfluxDB. Ingest, query, and analyze billions of data points in real-time with unbounded cardinality.

  

• quaterion

  4 622 2.3 Python

  Blazing fast framework for fine-tuning similarity learning models

  

PML is a great collection of implementations, but not the best framework. Also you can use PML with Quaterion: https://github.com/qdrant/quaterion/blob/master/examples/tra...

• qdrant

  140 17,839 9.9 Rust

  Qdrant - High-performance, massive-scale Vector Database for the next generation of AI. Also available in the cloud https://cloud.qdrant.io/

  

To answer my own question:

https://qdrant.tech/

• awesome-metric-learning

  3 433 1.8

  😎 A curated list of awesome practical Metric Learning and its applications

  

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

• Milvus

  104 26,857 10.0 Go

  A cloud-native vector database, storage for next generation AI applications

  

Great article. I've been working in and around this space since 2014, and I think similarity learning, vector search, and embedding management will be a core part of future applications that leverage ML.

I recently built a similarity search application that recommends new Pinterest users channels to follow based on liked images using Milvus (https://github.com/milvus-io/milvus) as a backend. Similarity learning is a huge part of it, and I'm glad more and more tools like Quaterion are being released to help make this kind of tech ubiquitous.

Suggest a related project