LOCL: Learning Object-Attribute Composition using Localization

10/07/2022
by   Satish Kumar, et al.
0

This paper describes LOCL (Learning Object Attribute Composition using Localization) that generalizes composition zero shot learning to objects in cluttered and more realistic settings. The problem of unseen Object Attribute (OA) associations has been well studied in the field, however, the performance of existing methods is limited in challenging scenes. In this context, our key contribution is a modular approach to localizing objects and attributes of interest in a weakly supervised context that generalizes robustly to unseen configurations. Localization coupled with a composition classifier significantly outperforms state of the art (SOTA) methods, with an improvement of about 12 modularity enables the use of localized feature extractor to be used with existing OA compositional learning methods to improve their overall performance.

READ FULL TEXT

Please sign up or login with your details

Forgot password? Click here to reset