Search Results for author:
Found 3 papers, 0 papers with code
Improving Generalization via Attribute Selection on Out-of-the-box Data
Unfortunately, previous attribute selection methods are conducted based on the seen data, and their selected attributes have poor generalization capability to the unseen data, which is unavailable in the training stage of ZSL tasks.
Learning Image-Specific Attributes by Hyperbolic Neighborhood Graph Propagation
In most of existing attribute-based research, class-specific attributes (CSA), which are class-level annotations, are usually adopted due to its low annotation cost for each class instead of each individual image.
Complementary Attributes: A New Clue to Zero-Shot Learning
Extensive experiments on five ZSL benchmark datasets and the large-scale ImageNet dataset demonstrate that the proposed complementary attributes and rank aggregation can significantly and robustly improve existing ZSL methods and achieve the state-of-the-art performance.
Cannot find the paper you are looking for? You can
Submit a new open access paper.
