Zero-shot learning, a special case of unsupervised domain adaptation where the source and target domains have disjoint label spaces, has become increasingly popular in the computer vision community. In this paper, we propose a novel zero-shot learning method based on discriminative sparse non-negative matrix factorization. The proposed approach aims to identify a set of common high-level semantic components across the two domains via non-negative sparse matrix factorization, while enforcing the representation vectors of the images in this common component-based space to be discriminatively aligned with the attributebased label representation vectors. To fully exploit the aligned semantic information contained in the learned representation vectors of the instances, we develop a label propagation based testing procedure to classify the unlabeled instances from the unseen classes in the target domain. We conduct experiments on four standard zero-shot learning image datasets, by comparing the proposed approach to the state-of-the-art zero-shot learning methods. The empirical results demonstrate the efficacy of the proposed approach.

Additional Metadata
Persistent URL dx.doi.org/10.1109/CVPR.2017.542
Conference 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017
Citation
Ye, M. (Meng), & Guo, Y. (2017). Zero-shot classification with discriminative semantic representation learning. In Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017 (pp. 5103–5111). doi:10.1109/CVPR.2017.542