1
$\begingroup$

I've been reading a lot lately about self-supervised learning and I didn't understand very well how to generate the desired label for a given image.

Let's say that I have an image classification task, and I have very little labeled data.

How can I generate the target label from the other data in the dataset?

$\endgroup$
1
$\begingroup$

If $D = \{ A, B \}$ is a dataset that contains both labelled and unlabelled data, where $A = \{ (x_i, y_i) \}_{i=1}^n$, $B = \{ x_i \}_{i=1}^m$, and $m \gg n$, then, to use self-supervised learning (for representation learning), you could follow these steps

  1. learn representations of your images $x_i$ by training a neural network $M$ with $B$ to solve a so-called pretext (or auxiliary task); there are many pre-text tasks: you can find many examples here; this step is the self-supervised learning part;

  2. use transfer learning to fine-tune $M$ with $A$, in a supervised way

Note that this answer is only based on my theoretical knowledge of the topic. Maybe you should have a look at existing implementations of SSL techniques for more inspiration! Moreover, note that you can also use semi-supervised learning techniques in your case.

| improve this answer | |
$\endgroup$
  • $\begingroup$ Thanks for the answer. I used semi supervised for autoencoders, but i don't have a clue how to use semi supervised for image classification or document classification :) $\endgroup$ – Vesko Vujovic Aug 4 at 11:58

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.