Faiss: A library for efficient similarity search - Facebook Engineering
This month, we released Facebook AI Similarity Search (Faiss), a library that allows us to quickly search for multimedia documents that are similar to each other — a challenge where traditional query search engines fall short. We’ve built nearest-neighbor search implementations for billion-scale data sets that are some 8.5x faster than the previous reported state-of-the-art, [...]Read More...
29 Mar 2017 ... This month, we released Facebook AI Similarity Search (Faiss), ... For example, an image collection would be represented as a table with one ...