Lecture 11: Detection and Segmentation (CS231n)

In Lecture 11 we move beyond image classification, and show how convolutional networks can be applied to other core computer vision tasks. We show how fully convolutional networks equipped with downsampling and upsampling layers can be used for semantic segmentation, and how multitask losses can be used for localization and pose estimation. We discuss a number of methods for object detection, including the region-based R-CNN family of methods and single-shot methods like SSD and YOLO. Finally we show how ideas from semantic segmentation and object detection can be combined to perform instance segmentation.

Keywords: Semantic segmentation, fully convolutional networks, unpooling, transpose convolution, localization, multitask losses, pose estimation, object detection, sliding window, region proposals, R-CNN, Fast R-CNN, Faster R-CNN, YOLO, SSD, DenseCap, instance segmentation, Mask R-CNN