BAP
Hanhui Li, Donghui Li, Xiaonan Luo · ACM International Conference on Multimedia (ACM MM) · 2014
Recent advances in attribute-based methods provide the zero-shot learning problem with practical solutions. In attribute-based methods, visual attributes are introduced to fill the gap between low-level image features and high-level semantic information. This paper proposes a novel bimodal attribute prediction model called BAP, which can better predict visual attributes in images. BAP fuses advantages of the conventional direct attribute prediction (DAP) and indirect attribute prediction (IAP) on the level of attribute prediction. It contains an attribute-classifier pooling process that generates a large amount of base classifiers and a combination strategy that integrates these classifiers. We explore and propose four BAP models with different combination strategies in this paper, and experimentally show that our BAP outperforms the conventional models both in offline and online zero-shot image categorization.
Cited by 12 works. doi:10.1145/2647868.2655023
Authors
References
- Learning to detect unseen object classes by between-class attribute transfer
- Learning to detect unseen object classes by between-class attribute transfer
- Decision templates for multiple classifier fusion: an experimental comparison
- A Discriminative Latent Model of Object Classes and Attributes
- Hi, magic closet, tell me what to wear!
- WhittleSearch: Image search with relative attribute feedback
- Online incremental attribute-based zero-shot learning
- Attribute Dominance: What Pops Out?
- Correlated attribute transfer with multi-task graph-guided fusion