bad performance of Attention RPN in base training

[Fly-dream12]

When i train the attention rpn model in the base training stage, the performance is bad and far away from that of other detectors (meta rcnn), what may be the reason? By the way, is the way always set as 2, and how is the shot is set, it is inconsistent with the shot num in config files (such as shot=9 in 10shot config yaml file). Thanks

[linyq17]

In my view, attention rpn requires high-quality (large and full objects are preferred) support instances for training and needs to carefully set the fine-tuning parameters, since attention rpn tends to overfit under few shot settings. The mmfewshot implementation of attention rpn only supports 2 ways. Since the sampling logic of attention rpn is query aware that means the support samples are selected according to the query images in the mini-batch, while methods like meta-rcnn the support samples are selected independently of query images in the mini-batch. In attention rpn, the query images in the mini-batch can not be used as support images, so 10 shot instances only can select 9 shot for support instance and 1 shot for query.

[leader402]

I have the same problem. Can you provide normal training parameters?

Environment is single 3090