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
Paper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Semantic Segmentation | 99 | 11.02% |
Named Entity Recognition (NER) | 64 | 7.13% |
NER | 44 | 4.90% |
Image Segmentation | 37 | 4.12% |
Sentence | 30 | 3.34% |
General Classification | 23 | 2.56% |
Object Detection | 18 | 2.00% |
Part-Of-Speech Tagging | 17 | 1.89% |
Language Modelling | 13 | 1.45% |
Component | Type |
|
---|---|---|
🤖 No Components Found | You can add them if they exist; e.g. Mask R-CNN uses RoIAlign |