-
In the code, it seems that u didn't calculate the text_prototype alignment loss. As in the initialize of Contrastive_loss, the text_prototype is setting default as False. (self.loss = losses.contrasti…
-
Hi, thanks for your great work!
I have a question about contrastive loss.
What does (Ypos, Yneg, Yanchor) stand for?
-
Hi Kevin
Would you mind add my Selectively Contrastive Triplet loss (which is published in ECCV2020)? The major idea of this paper is to overcome the local minima during the triplet optimization. T…
-
Hi, thank you for your awesome work, the experiment results of the code are quite consistent with the paper.
I have some question about the role of contrastive learning in SGL, I notice that in the t…
zwb29 updated
2 years ago
-
### Background
A loss function suitable for unsupervised learning would contribute to extending ProgLearn's training domain to unsupervised settings in which labeled data are not available.
The…
-
Hi, Thanks for sharing your amazing work!
How should I use the Contrastive Loss function in the table classification task?
-
Hello,
great work!
Do you perform any (differentiable) augmentations on the image patches before feeding them into the encoder-part of the generator, as is common in contrastive learning?
I'm hav…
jwb95 updated
2 years ago
-
input tensor to SupConLoss need to have 3 dimenstion.
batch size, 2(two features made from augmentation), z_dim(128)
if I dont want augmentation,
[batch size, 1, z_dim(128)] is ok for SupConLo…
-
Implement contrastive loss function according to paper:
http://yann.lecun.com/exdb/publis/pdf/hadsell-chopra-lecun-06.pdf
-
hi, i am confused about how to compute the contrastive loss in the paper, as it mentioned in the paper to calculate lret through (t,t',y,y') , but in the code, the model returns (cpt - 0.5) * 2, cls,…