Sign Up to like & get
recommendations!
0
Published in 2018 at "Neural Computation"
DOI: 10.1162/neco_a_01071
Abstract: Due to the difficulty of collecting labeled images for hundreds of thousands of visual categories, zero-shot learning, where unseen categories do not have any labeled images in training stage, has attracted more attention. In the…
read more here.
Keywords:
maximum mean;
mean discrepancy;
shot learning;
zero shot ... See more keywords