Hello,

So, i am working on a bit of a complex problem where I want to detect faults of a system using sensors data including cameras.

Since i only need two states pass / fail as output, I directed my attention to contrastive learning (specificlly self-supervised) version of it.

I am currently facing a challenge in defining the positive and negative pairs for training. In principle, I should use the image and its augmented versions as +ve pairs and the image and all other images as -ve. However, this is problematic as the other images may not be dissimilar.

So, any suggestions on how to tackle this problem ?

Thanks