Why the MMA is so low when threshold lower than 4px?
Closed this issue · 1 comments
ChunhuanLin commented
In Figure 4 of your paper, we can see that the trained D2-Net have low MMA when the threshold is small? It seems strange since it's even performs worse than the not trained version.
mihaidusmanu commented
That's in part expected since the description / detection is trained coarsely (grid with stride 8), due to the max-poolings in the VGG network. The features are detected with a spatial stride of 4 / 8 px - test / train. An error of 4px means exactly one pixel off (at test feature map resolution) without the order-2 keypoint refinement (which is not considered during training).