Abstract | ||
---|---|---|
We study zero-shot learning (ZSL) as a transfer learning problem, and focus on the two key aspects of ZSL, model effectiveness and model adaptation. For effective modeling, we adopt the boosting strategy to learn a zero-shot classifier from weak models to a strong model. For adaptable knowledge transfer, we devise a Semantic Correlation Regularization (SCR) approach to regularize the boosted model to be consistent with the inter-class semantic correlations. With SCR embedded in the boosting objective, and with a self-controlled sample selection for learning robustness, we propose a unified framework, Boosted Zero-shot classification with Semantic Correlation Regularization (BZ-SCR). By balancing the SCR-regularized boosted model selection and the self-controlled sample selection, BZ-SCR is capable of capturing both discriminative and adaptable feature-to-class semantic alignments, while ensuring the reliability and adaptability of the learned samples. The experiments on two ZSL datasets show the superiority of BZ-SCR over the state-of-the-arts. |
Year | DOI | Venue |
---|---|---|
2017 | 10.24963/ijcai.2017/362 | IJCAI |
DocType | Volume | Citations |
Conference | abs/1707.08008 | 1 |
PageRank | References | Authors |
0.34 | 13 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Te Pi | 1 | 6 | 1.41 |
Xi Li | 2 | 1850 | 137.71 |
Zhongfei (Mark) Zhang | 3 | 2451 | 164.30 |