Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning

arXiv: Computer Vision and Pattern Recognition, Volume abs/1712.03151, 2017.

Cited by: 0|Bibtex|Views1|Links
EI

Abstract:

We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation. For both non-novel and novel image classes we compare multiple formulations of the problem, starting with deep universal features in each case. We investigate the effect of usi...More

Code:

Data:

Your rating :
0

 

Tags
Comments