原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Now, just like autoregressive models, diffusion models train a neural net, fθ, to reverse this process. It can be trained via supervised learning on examples sequences of different images getting noisier and noisier. For example, as shown below in figure 32.15, the sequence of images of the bird getting noisier and noisier can be flipped in time and thereby provide a sequence of training examples
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/c032.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8