We present a novel attribute learning framework named Hypergraph-based Attribute Predictor (HAP). In HAP, a hypergraph is leveraged to depict the attribute relations in the data. Then the attribute prediction problem is casted as a regularized hypergraph cut problem in which HAP jointly learns a collection of attribute projections from the feature space to a hypergraph embedding space aligned with the attribute space. The learned projections directly act as attribute classifiers (linear and kernelized). This formulation leads to a very efficient approach. By considering our model as a multi-graph cut task, our framework can flexibly incorporate other available information, in particular class label. We apply our approach to attribute prediction, Zero-shot and N-shot learning tasks. The results on AWA, USAA and CUB databases demonstrate the value of our methods in comparison with the state-of-the-art approaches.
@article{arxiv.1503.05782,
title = {Learning Hypergraph-regularized Attribute Predictors},
author = {Sheng Huang and Mohamed Elhoseiny and Ahmed Elgammal and Dan Yang},
journal= {arXiv preprint arXiv:1503.05782},
year = {2015}
}
Comments
This is an attribute learning paper accepted by CVPR 2015