I am interested in inversing a transposed convolution operation (or "deconvolution", and not straightforward convolution).

A transposed convolution usually maps data points from a smaller feature space (latent space) onto a much larger feature space (image space), so the inverse should not be ambiguous, or should it?

Is there an established mathematical framework for performing the inversion? If not, how do you suggest approach the problem?

New contributor
Kang Min Yoo is a new contributor to this site. Take care in asking for clarification, commenting, and answering. Check out our Code of Conduct.

Your Answer

Kang Min Yoo is a new contributor. Be nice, and check out our Code of Conduct.

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

Browse other questions tagged or ask your own question.