facebookresearch / detr

End-to-End Object Detection with Transformers
Apache License 2.0
13.56k stars 2.45k forks source link

Do you report performance about instance segmentation? #74

Closed gaopengcuhk closed 4 years ago

gaopengcuhk commented 4 years ago

❓ How to do something using DETR

Describe what you want to do, including:

  1. what inputs you will provide, if any:
  2. what outputs you are expecting:

NOTE:

  1. Only general answers are provided. If you want to ask about "why X did not work", please use the Unexpected behaviors issue template.

  2. About how to implement new models / new dataloader / new training logic, etc., check documentation first.

  3. We do not answer general machine learning / computer vision questions that are not specific to DETR, such as how a model works, how to improve your training/make it converge, or what algorithm/methods can be used to achieve X.

gaopengcuhk commented 4 years ago

As the name implies, have you ever conduct any experiments on Mask RCNN?

alcinos commented 4 years ago

Hi @gaopengcuhk We haven't specifically explored instance segmentation. We report some AP numbers in last column of table 5 (trained on coco panoptic), but this is indicative only and we did not focus on that.

I think I have answered your question, and as such I'm closing this issue. If you have further questions, please reach out.