Zero-Shot learning (ZSL) recently has drawn a lot of attention due to its ability to transfer knowledge from seen classes to novel unseen classes, which greatly reduces human labor of labelling data for building new classifiers. Much effort on ZSL however has focused on the standard multi-class setting, the more challenging multi-label zero-shot problem has received limited attention. In this paper, we propose a transfer-aware embedding projection approach to tackle multi-label zero-shot learning. The approach projects the label embedding vectors into a low-dimensional space to induce better inter-label relationships and explicitly facilitate information transfer from seen labels to unseen labels, while simultaneously learning a max-margin multi-label classifier with the projected label embeddings. Auxiliary information can be conveniently incorporated to guide the label embedding projection to further improve label relation structures for zero-shot knowledge transfer. We conduct experiments for both standard zero-shot multi-label image classification and generalized zero-shot multi-label classification. The results demonstrate the efficacy of the proposed approach.

, , ,
26th IEEE International Conference on Image Processing, ICIP 2019
School of Computer Science

Ye, M. (Meng), & Guo, Y. (2019). Multi-Label Zero-Shot Learning with Transfer-Aware Label Embedding Projection. In Proceedings - International Conference on Image Processing, ICIP (pp. 3671–3675). doi:10.1109/ICIP.2019.8803720