From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis
This addresses the challenge of recognizing new classes without real images, which is incremental as it builds on existing zero-shot learning methods.
The paper tackles the problem of zero-shot learning by synthesizing visual features for unseen classes using semantic attributes, converting it into a supervised classification task. It reports significant improvements in state-of-the-art results on four benchmark datasets.
Robust object recognition systems usually rely on powerful feature extraction mechanisms from a large number of real images. However, in many realistic applications, collecting sufficient images for ever-growing new classes is unattainable. In this paper, we propose a new Zero-shot learning (ZSL) framework that can synthesise visual features for unseen classes without acquiring real images. Using the proposed Unseen Visual Data Synthesis (UVDS) algorithm, semantic attributes are effectively utilised as an intermediate clue to synthesise unseen visual features at the training stage. Hereafter, ZSL recognition is converted into the conventional supervised problem, i.e. the synthesised visual features can be straightforwardly fed to typical classifiers such as SVM. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data. Extensive experimental results suggest that our proposed approach significantly improve the state-of-the-art results.