原书出处
Foundations of Computer Vision (Antonio Torralba, Phillip Isola etc.)
Here we are applying random transformations to the data, and we want our learner to do well in expectation over these random transformations. Instead of doing random transformations, we could instead consider augmenting with worst case transformations, applying those transformations that incur the highest loss possible for a given training example:
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/c036.xhtml
EPUB SHA-256:60a7eebc43f5d9a675d776fed3736fbdaa791e55877023f2f8cba016a9b384f8