I have been trying to understand facebook's Detection transformer(DeTr) paper.


enter image description here Most of the explanation about the architecture is straightforward.
I don't especially understand the concept of object queries.


In the paper,

A transformer decoder then takes as input a small fixed number of learned positional embeddings, which we call object queries, and additionally attends to the encoder output.

There are 2 kinds of positional encodings in our model: spatial positional encodings(fixed) and output positional encodings(Object queries).

Learned positional encodings and output positional encodings are same.


  1. What are these "learned" positional encodings(object queries)?
  2. how are they different from spatial positional encodings?
  3. When are they exactly learned?

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.