search

jwyang / graph-rcnn.pytorch

[ECCV 2018] Official code for "Graph R-CNN for Scene Graph Generation"
727 stars 158 forks source link

NMS in Relation Proposal Network #92

Closed sharifza closed 4 years ago

sharifza commented 4 years ago

https://github.com/jwyang/graph-rcnn.pytorch/blob/be9d901a2cdecda3669eb780a3f437d6c3e061b9/lib/scene_parser/rcnn/modeling/relation_heads/relpn/relpn.py#L241

Hi! Based on the implementation in part of the repo, can I assume that your current implementation (and results) of RePN does not have the IoU-based NMS step described by Eq.3 of the paper? Was there a reason to take it out?

jwyang commented 4 years ago

Hi, @sharifza . Yes, there is indeed a reason to take it out. In our original paper, as mentioned in README, we did not do the per-class NMS to filter the bounding boxes from object detection module, and thus the Co-NMS is essential to filter the highly-overlapped box-pairs from the candidates. However, in current implementation, we added the per-class NMS as Neural MotifNet since it improved the performance significantly, so there is no necessary to re-run the Co-NMS on top of the box-pairs any more. As a byproduct, this also saves time. Let me know you still have confuse.

sharifza commented 4 years ago

Thanks for clarification (maybe you can explicitly mention this in the readme since its an important difference with the paper)