Back to feed

RelateAnything: Predicting Relationships in Images

RelateAnything is a real-time model for predicting relationships between objects in images with an open predicate vocabulary.

How the system works

The model takes an image and regions of interest from any source, returning estimated relationships based on predicates defined during inference as strings.

Key features of RelateAnything

  • Does not require object labels as input data
  • Allows using various region sources without retraining
  • Works with an open predicate vocabulary
11.4K views

More from this channel Open Source

Similar in this category Technology

New DDoS Attack on Beget Hosting

New DDoS Attack on Beget Hosting

Hosting provider Beget has been subjected to a new DDoS attack, aimed at disrupting recovery processes following the previous breach. Some users have experienced disruptions in accessing services.

Technology