Image retrieval is the process of searching for images in a large database that are similar to one or more query images. A classical approach is to transform the database images and the query images into embeddings via a feature extractor (e.g., a CNN or a ViT), so that they can be compared via a distance metric. Self-supervised learning (SSL) can be used to train a feature extractor without the need for expensive and time-consuming labeled training data. We will use DINO's SSL method to build a feature extractor and Milvus, an open-source vector database built for evolutionary similarity search, to index image representation vectors for efficient retrieval. We will compare the SSL approach with supervised and pre-trained feature extractors.

Antoine Toubhans

Affiliation: Sicara

Python developer and Data-Scientist, I am Head of Science at Sicara since 2018.

I am also the organizer of the Paris Computer Vision Meetup.

Speaker at PyConUS22 and PyDataBerlin22.

visit the speaker at: Github

Noé Achache

Affiliation: Sicara

Noé is a lead data scientist at Sicara, and worked on various AI and data engineering related projects. Speaker at the Paris Computer Vision Meetup.

visit the speaker at: Github