Search Results for author:
Found 2 papers, 1 papers with code
Simple Semantic-Aided Few-Shot Learning
This limitation severely constrains the potential of semantics in Few-Shot Learning.
Attribute Localization and Revision Network for Zero-Shot Learning
Second, we propose Attribute Revision Module (ARM), which generates image-level semantics by revising the ground-truth value of each attribute, compensating for performance degradation caused by ignoring intra-class variation.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
