Closed vadimkantorov closed 6 years ago
D represents dissimilarity between receptive fields, and the random walker accumulates mass at nodes that have high dissimilarity with other nodes, thus salient object regions get high objectness confidence other than backgrounds. The normalized spatial distance is a kind of weight for feature dissimilarity.
I kind of understand now. Thanks!
Can you please clarify this line https://github.com/yeezhu/SPN.pytorch/blob/master/spnlib/spn/src/generic/SoftProposalGenerator.cu#L117 (kernel_(UpdateProposal))?
If I understand well, it does M = M + DM
(instead of M = DM
in the paper). Am I right?
Got it. Thanks!
In the paper and the code you define D as:
D(ij, pq) = ||u_ij - u_pq|| * exp(-((i - p)**2 + (j - q)**2)/(2 * sigma**2))
whereu
is the features tensor, andi,j,p,q
are coordinates of two feature vectors.The first term is dissimilarity (when it's large, features are very dissimilar), the second is similarity (when it's large, features are very close geometrically). Please correct me if I'm getting it wrongly.
During update of objectness vector:
M_i = \sum_j M_j * D_ji
, i.e.M_i
will have high objectness if locationsj
have high objectness and are dissimilar toi
.Does it make sense to mix dissimilarity and similarity?
Thanks!