原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Thinking of dϕ as a learned loss function raises new questions: What does this loss function penalize, and how can we control its properties. One of the main levers we have is the architecture of dϕ; different architectures will have the capacity, and/or inductive bias, to penalize different kinds of errors. One popular architecture for image-to-image tasks is a PatchGAN discriminator [232], in which we
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/c034.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8