search

impiga / Plain-DETR

[ICCV2023] DETR Doesn’t Need Multi-Scale or Locality Design
MIT License
192 stars 4 forks source link

Question about the BoxRPB #5

Closed Adlith closed 12 months ago

Adlith commented 1 year ago

Congratulations on the great work. How can you get the coordinate of K predicted boxes to generate BoxRPB before cross-attention?

PkuRainBow commented 1 year ago

We will release the source code soon.

ChaseMonsterAway commented 1 year ago

We will release the source code soon.

Could you give us an estimate of when?

PkuRainBow commented 1 year ago

@impiga Yutong is currently in the process of finalizing the code and checkpoints. We invite you to stay tuned for updates.

impiga commented 12 months ago

Hi, @Adlith

We adopt the two-stage setting following Deformable DETR. So, the model would generate bounding box proposals prior to executing the Decoder.