Appendix B
Object Detection and Segmentation
This appendix logically follows Chapter 8, “Deeper CNNs and Pretrained Models.”
Our detailed descriptions of convolutional networks in Chapter 7, “Convolutional Neural Networks Applied to Image Classification,” and Chapter 8 focused on object classification. The objective was to determine which one, out of a large number of classes, the image represented. This is a fairly simplified view of the world. It is often the case that an image contains many different objects belonging to different classes, which results in more complicated tasks. Three such tasks are object detection, semantic segmentation, and instance segmentation. They are all illustrated in Figure B-1. Object detection involves identifying ...
Get Learning Deep Learning: Theory and Practice of Neural Networks, Computer Vision, NLP, and Transformers using TensorFlow now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
