5,337
edits
Visual Learning and Recognition: Difference between revisions
→Semantic Segmentation
| Line 442: | Line 442: | ||
Given an image, label every pixel with a class. | Given an image, label every pixel with a class. | ||
Note object segmentation is semantic segmentation with just one class. | Note object segmentation is semantic segmentation with just one class. | ||
Segmentation does not give us instances unlike object detection. | Segmentation does not give us instances unlike object detection. | ||
Instance segmentation is object segmentation + detection. | |||
;Energy function | |||
* Labels a pixel | |||
* Penalty if label is unlikely | |||
===MRF=== | |||
Markov random field | |||
===CRF=== | |||
Conditional random field | |||
'''Read TextonBoost ECCV 2006''' | |||
===Superpixels=== | |||
;TODO | |||
* '''Read SSD, YOLO, TexonBoost''' | |||
==Will be on the exam== | ==Will be on the exam== | ||