Some concepts are easy to confuse, tidy up, note memory. 1. Image classification to identify the content in the image; 2. Object recognition and Detection identify the content and location in the image (through the boundary box); 3. Semantic segmentation identifies the content and location in the image (by searching all pixels belonging to it). Semantic segmentation is a problem in computer vision that involves taking raw data (for example, flat images) and converting them into areas of interest that stand out. Can be divided into: (1) Standard Semantic segmentation (2) Instance Aware Semantic segmentation Standard semantic segmentation, also known as full-pixel Semantic segmentation, is the process of classifying each pixel into object classes. Instance-aware semantic segmentation is a subtype of standard semantic segmentation, which classifies each pixel into object class and entity ID of that class. For example, semantic segmentation thinks they are all people; Instance segmentation thinks they are different people, different objects. — — — — — — — — — — — — — — — — — — — — – the author: scampering lambs source: CSDN, blog.csdn.net/yql_6175402… Copyright notice: This article is the blogger’s original article, reprint please attach the blog link!
More learning materials can be obtained at Annalin1203