'a mask prediction' in Sec. 3.2.2 of Paper
Closed this issue · 5 comments
Huster-Hq commented
hkchengrex commented
Yes.
Huster-Hq commented
I have a question about the detail of Object Memory:
- The object memory are computed by N pooling masks
$W$ . However, these pooling masks do not have a constraint label, unlike the mask$M_l$ projected from the pixel features constrained by GT mask. I can't understand the information contained in these pooling masks and why one half can be foreground predictions and the other half is background predictions. I wonder if you have directly visualized these masks.
Huster-Hq commented
Huster-Hq commented
What do you mean by "constraint label"? W is directly constructed from M_l in the screenshot that you provided. There are no additional transformations. Those masks are just the masks in Figure 4 (and their inverse).
Figure 4 shows the
hkchengrex commented
Oh, right. Sorry -- it slipped my mind. We have visualized them before at some point. IIRC those masks are rather diffuse and don't have very recognizable patterns. They are learned end-to-end.