原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
An object is something localized in space. There are other things that are not localized such as fog, light, and so on. Not everything is well-described by a bounding box (stuff, wiry objects, etc.). Instead we can try to classify each pixel in an image with an object class. Per-pixel classification of object labels, illustrated in figure 50.20, is referred to as semantic segmentation.
原书定位详情
来源:a19c7933-4eda-4176-aebd-30fe7e1ad292
正文位置:extracted/Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)/_epub-src/OPS/xhtml/c050b.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8