cs330
以上14节课
为什么看到metalearning ?
Multi-Domain Data. It is well recognized that there is
a large domain gap between different datsets [35]. Most
existing methods adopt domain adaptation for cross-dataset
training. A more practical solution would be learning a domain generalized model with a number of source datasets,
such that the learned model can be generalized to new
unseen datasets for discriminative Re-ID without additional
training [106]. The Domain-Invariant Mapping Network
(DIMN) [106] starts the first attempt by designing a metalearning pipeline, learning a mapping between a person
image and its identity classifier.