From Zero-shot Learning to Conventional Supervised Classification: Unseen Visual Data Synthesis

Abstract

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.

References in corpus (5)

• Transductive Multi-view Zero-Shot Learning
• Zero-Shot Learning via Semantic Similarity Embedding
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• Learning Hypergraph-regularized Attribute Predictors
• Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning

Cited by in corpus (5)

• Fine-Grained Zero-Shot Learning with DNA as Side Information
• Classifier and Exemplar Synthesis for Zero-Shot Learning
• CIZSL++: Creativity Inspired Generative Zero-Shot Learning
• Adaptive Adjustment with Semantic Feature Space for Zero-Shot Recognition
• Mitigating Generation Shifts for Generalized Zero-Shot Learning