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 80 12.90%
Named Entity Recognition 59 9.52%
NER 43 6.94%
General Classification 24 3.87%
Part-Of-Speech Tagging 14 2.26%
Object Detection 12 1.94%
Chunking 11 1.77%
Machine Translation 11 1.77%
Depth Estimation 10 1.61%

Components


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

Categories