Semi-supervised Zero-Shot Learning by a Clustering-based Approach
This work addresses object recognition for scenarios with limited labeled data, representing an incremental improvement over existing zero-shot learning methods.
The paper tackles the problem of zero-shot learning where labeled data is unavailable for some categories, proposing a semi-supervised method that maps signatures to visual features to improve classification. It demonstrates effectiveness by improving state-of-the-art prediction accuracy on three out of four public benchmarks.
In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can recognize samples from categories with no labeled instance. In this paper, we propose a novel semi-supervised zero-shot learning method that works on an embedding space corresponding to abstract deep visual features. We seek a linear transformation on signatures to map them onto the visual features, such that the mapped signatures of the seen classes are close to labeled samples of the corresponding classes and unlabeled data are also close to the mapped signatures of one of the unseen classes. We use the idea that the rich deep visual features provide a representation space in which samples of each class are usually condensed in a cluster. The effectiveness of the proposed method is demonstrated through extensive experiments on four public benchmarks improving the state-of-the-art prediction accuracy on three of them.