Image search with localization and open-vocabulary reranking using Marqo, yolox, CLIP and OWL-ViT

This page summarizes the projects mentioned and recommended in the original post on dev.to
Deep Learning Search information-retrieval Machinelearning

InfluxDB
Our great sponsors
  • InfluxDB - Power Real-Time Data Analytics at Scale
  • WorkOS - The modern identity platform for B2B SaaS
  • SaaSHub - Software Alternatives and Reviews
Our great sponsors

  • marqo

    Unified embedding generation and search engine. Also available on cloud - cloud.marqo.ai

    TL;DR: Here we show how image search can be evolved to add localization and re-ranking by leveraging Marqo, yolox, CLIP and OWL-ViT. Adding the extra dimension of localization can improve retrieval performance and enable new use cases for image search while also helping with explainability. Re-ranking with an open vocabulary detection model allows for even finer-grained localsiation. The first part of the article covers background information while the second part contains working code (also found here).

  • InfluxDB

    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.

NOTE: The number of mentions on this list indicates mentions on common posts plus user suggested alternatives. Hence, a higher number means a more popular project.

Suggest a related project

Related posts