I came across the application of a conditional random field (CRF) to the output from a convolutional neural network (CNN) for image segmentation. The additional CRF step seems to be a common technique for image segmentation and as a post-processing step in CNNs for segmentation.

I began looking into how they work which lead me to a course on probabilistic graphical models by Daphne Koller on Coursera.

I found this course to be useful, but very general.

My question is: what is a good text or course to study the construction and training of CRFs, preferably one that starts with a gentle introduction assuming no prior background?


andrew maccallum has an excellent article on CRFs - https://people.cs.umass.edu/~mccallum/papers/crf-tutorial.pdf

There has to be a few assumptions on prior background like probability and general math.

| cite | improve this answer | |

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.