Two-modal paired image data by:
1) private-1 = elevation (illumination = neutral value fixed)
2) private-2 = illumination (elevation = neutral value fixed)
3) shared = (azimuth, id)
Let: xI = modality 1, xT = modality 2
(at iter 300K)
3 instances, each:
True xI | xI w/ zI(1) change | xI w/ zI(2) | xI w/ zS(1) | xI w/ zS(2) | ... | xI w/ zT(1) | xI w/ zT(2)
True xT | xT w/ zI(1) change | xT w/ zI(2) | xT w/ zS(1) | xT w/ zS(2) | ... | xT w/ zT(1) | xT w/ zT(2)
(note: quite accurately identify private and shared factors, but computational issue of having dyadic inf net)
3 instances, each:
True xI | xI w/ z(1) change | xI w/ z(2) | ... | xI w/ z(10)
True xT | xT w/ z(1) change | xT w/ z(2) | ... | xT w/ z(10)
(note: variation of z(4) or z(7), none of them shared factors, results in changes in both xI and xT)
3 instances, each:
True xI | xI w/ zI(1) change | xI w/ zI(2) | xI w/ zS(1) | xI w/ zS(2) | ... | xI w/ zT(1) | xI w/ zT(2)
True xT | xT w/ zI(1) change | xT w/ zI(2) | xT w/ zS(1) | xT w/ zS(2) | ... | xT w/ zT(1) | xT w/ zT(2)
(note: problematic! eg, zS(1) learns elevation factor, but it should be a private factor in zI)
3 instances, each:
True xI | xI w/ zI(1) change | xI w/ zI(2) | xI w/ zS(1) | xI w/ zS(2) | ... | xI w/ zT(1) | xI w/ zT(2)
True xT | xT w/ zI(1) change | xT w/ zI(2) | xT w/ zS(1) | xT w/ zS(2) | ... | xT w/ zT(1) | xT w/ zT(2)
(note: better identify/discern the private and shared factors, which implies that the loss terms for marginal data, ie, {xI} and {xT}, are necessary?)
3 instances, each:
True xI | xI w/ z(1) change | xI w/ z(2) | ... | xI w/ z(10)
True xT | xT w/ z(1) change | xT w/ z(2) | ... | xT w/ z(10)
3 instances, each:
True xI | xI w/ z(1) change | xI w/ z(2) | ... | xI w/ z(10)
True xT | xT w/ z(1) change | xT w/ z(2) | ... | xT w/ z(10)
(at iter 300K)
[xI, xT]
[xI, xT]
[xI, xT]
(note: the quality of generated images is not satisfactory.. especially when compared to the v2 model below)
[xI, xT]
[xI, xT]
[xI, xT]
(at iter 300K)
XI -> XT [XI | three randomly synthesized XT images]
(note: in the synthesized XT images, illumination (private-T) can vary, but elevation (private-I) should be neutral, and (azimuth, id) should be identical to those of XI)
XT -> XI
[XT | three randomly synthesized XI images]
(note: in the synthesized XI images, elevation (private-I) can vary, but illumination (private-T) should be neutral, and (azimuth, id) should be identical to those of XT)
Of course, N/A
XI -> XT
[XI | three randomly synthesized XT images]
XT -> XI
[XT | three randomly synthesized XI images]
(note: again, v1 suffers from poor quality of synthesized images. It seems to be necessary to take into account the marginal data {xI} and {xT} in the training..)
XI -> XT
[XI | three randomly synthesized XT images]
XT -> XI
[XT | three randomly synthesized XI images]
XI -> XT
[XI | a synthesized XT image]
XT -> XI
[XT | a synthesized XI image]
XI -> XT
[XI | a synthesized XT image]
XT -> XI
[XT | a synthesized XI image]