train_hallucination vs train_hallucination_p2 for NYUD about admd HOT 9 CLOSED

Hi,

• train_hallucination is naive adversarial with square loss.

• train_hallucination_p2 implements equations (1) and (2) in the paper. Please check them carefully. Note that the one-hot vector in the code has length self.no_classes + 1, meaning that the discriminator has to distinguish between hallucinated and depth features, but in the case of depth features it also has to select the correct class. The loss merges the adversarial problem and the classification problems by having self.no_classes + 1 classes, where the +1 accounts for the 'hallucination' class.

Results for NYUD are listed in the last two lines of Table 4.

from admd.

Ok so train_hallucination (naive adversarial with square loss) is your older paper right?

If you are referring the ECCV paper reference [11] the answer is no. That is the line above in Table 4.

from admd.

My mistake. 3072 should be the correct one, but 4 more neurons would certainly make no difference.

from admd.

Thanks. Also seem you have an error in your paper for the discriminator...It's written For the task of action recognition, the structure is quite shallow, consisting in D1=[fc(2048), fc(1024), fc(C+1)]. For the task of object classification the structure is instead more complex D2=[fc(1024), fc(1024), fc(1024), fc(2048), fc(3072), fc(C+1)], with skip connections in the lower layers. But figure 4 presents the opposite...

from admd.

Hi,

• train_hallucination is naive adversarial with square loss.
• train_hallucination_p2 implements equations (1) and (2) in the paper. Please check them carefully. Note that the one-hot vector in the code has length self.no_classes + 1, meaning that the discriminator has to distinguish between hallucinated and depth features, but in the case of depth features it also has to select the correct class. The loss merges the adversarial problem and the classification problems by having self.no_classes + 1 classes, where the +1 accounts for the 'hallucination' class.

Results for NYUD are listed in the last two lines of Table 4.

Ok so train_hallucination (naive adversarial with square loss) is your older paper right?

from admd.

Thanks. Also seem you have an error in your paper for the discriminator...It's written For the task of action recognition, the structure is quite shallow, consisting in D1=[fc(2048), fc(1024), fc(C+1)]. For the task of object classification the structure is instead more complex D2=[fc(1024), fc(1024), fc(1024), fc(2048), fc(3072), fc(C+1)], with skip connections in the lower layers. But figure 4 presents the opposite...

Yes you are right, the caption is inverted.

from admd.

Thank you for your very quick answers!

from admd.

Glad to help :)

from admd.

Oh I have one more question: in Fig. 4 for the last fc layer of the discriminator on the right the number is 3072, while in your code its 3076, what should I use ?

from admd.