Paper

Improving Generalization via Attribute Selection on Out-of-the-box Data

Zero-shot learning (ZSL) aims to recognize unseen objects (test classes) given some other seen objects (training classes), by sharing information of attributes between different objects. Attributes are artificially annotated for objects and treated equally in recent ZSL tasks... (read more)

Results in Papers With Code
(↓ scroll down to see all results)