5,337
edits
Visual Learning and Recognition: Difference between revisions
→Overfeat
| Line 435: | Line 435: | ||
;Efficient sliding window | ;Efficient sliding window | ||
Use a fully convolutional network. | Use a fully convolutional network. | ||
===Single Stage Multibox Detector (SSD)=== | |||
===YOLO=== | |||
==Semantic Segmentation== | |||
Given an image, label every pixel with a class. | |||
Note object segmentation is semantic segmentation with just one class. | |||
Segmentation does not give us instances unlike object detection. | |||
==Will be on the exam== | ==Will be on the exam== | ||