FPN baseline about relation-networks-for-object-detection

[stupidZZ]

@FishYuLi Some other known differences are:

1. The detectron changes the learning rate by 2 times, there has 0.2~0.4 mAP improvement.
2. The implementation of weight-decay in MXNET and Caffe2 has a little difference, this may lead 0.1~0.3 mAP gaps compared with the best results, depending on how many GPUs do you use.
3. We closed the warmup.
4. The detectron adopts Xariver init, we use random Gaussian.
5. We use softnms=0.6 and the detectron use NMS=0.5. For plain ROI, the softnms will have 0.4~0.5 mAP gain than NMS. But for ROI-Align, there is only 0.2 mAP gain.

[chengdazhi]

A difference is that detectron use RoIAlign, where we use RoIPool.

[FishYuLi]

@chengdazhi Yes, I notice that. But I'm not sure that if RoIAlign can make a difference of nearly 1.7 points. The paper of Mask RCNN shows that this may lead to an improvement of about 1 point, which makes me a little confused.
Thanks a lot. I may try RoIAlign later.

[chengdazhi]

Another possibility is that we train FPN in a two stage manner, this speeds up training, but can harm accuracy.

[FishYuLi]

@chengdazhi 38.5 is also the result of a two-stage manner with pre-computed proposals and 1x schedule. They got 39.4 with end2end training.

[chengdazhi]

different pretrained resnet models could be another possible cause

[FishYuLi]

@stupidZZ Sounds more reasonable. Thanks! : )