search

megvii-research / FSCE

Apache License 2.0
275 stars 47 forks source link

Variants about MoCo and Prototype #17

Closed Chen-Song closed 3 years ago

Chen-Song commented 3 years ago

In your code, there are some variants based on MoCo ("eg, ContrastiveROIHeadsWithStorage") or Prototype ("eg, ContrastiveROIHeadsWithPrototype"). What is the final result (nAP) of these two variants? Will it be much lower than the optimal result reported in the paper?

bsun0802 commented 3 years ago

The prototype turns out to be not helping or damaging the results.

The momentum encoding seems to be a bit lower than reported in the paper, tested on VOC Split 1 and get nAP=61+. But the code might not be necessary with the one uploaded here (shouldn't have uploaded those ..).

Chen-Song commented 3 years ago

In your code: _C.MODEL.ROI_BOX_HEAD.CONTRASTIVE_BRANCH.PROTOTYPE.PATH = '' self.prototype_path = cfg.MODEL.ROI_BOX_HEAD.CONTRASTIVE_BRANCH.PROTOTYPE.PATH prototype_tensor = torch.load(self.prototype_path) # [num_classes+1, 1024]

Is PROTOTYPE.PATH empty?

Chen-Song commented 3 years ago

In your code: _C.MODEL.ROI_BOX_HEAD.CONTRASTIVE_BRANCH.PROTOTYPE.PATH = '' self.prototype_path = cfg.MODEL.ROI_BOX_HEAD.CONTRASTIVE_BRANCH.PROTOTYPE.PATH prototype_tensor = torch.load(self.prototype_path) # [num_classes+1, 1024]

Is PROTOTYPE.PATH empty?