Structured Prediction

Conditional Random Field

Conditional Random Fields or CRFs are a type of probabilistic graph model that take neighboring sample context into account for tasks like classification. Prediction is modeled as a graphical model, which implements dependencies between the predictions. Graph choice depends on the application, for example linear chain CRFs are popular in natural language processing, whereas in image-based tasks, the graph would connect to neighboring locations in an image to enforce that they have similar predictions.

Image Credit: Charles Sutton and Andrew McCallum, An Introduction to Conditional Random Fields

Papers


Paper Code Results Date Stars

Tasks


Task Papers Share
Semantic Segmentation 98 10.84%
Named Entity Recognition (NER) 64 7.08%
NER 44 4.87%
Image Segmentation 37 4.09%
Sentence 30 3.32%
Test 29 3.21%
General Classification 23 2.54%
Part-Of-Speech Tagging 17 1.88%
Object Detection 17 1.88%

Components


Component Type
🤖 No Components Found You can add them if they exist; e.g. Mask R-CNN uses RoIAlign

Categories