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

TL;DR

This paper introduces a zero-shot learning framework that synthesizes visual features for unseen classes using semantic attributes, enabling conventional classifiers to recognize new categories without real images.

Contribution

The novel UVDS algorithm effectively synthesizes unseen visual features from semantic attributes, transforming zero-shot learning into a supervised classification problem.

Findings

Significant improvement over state-of-the-art results on four benchmark datasets.

Synthesized features enable effective classification of unseen classes.

Approach reduces reliance on real images for new class recognition.

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.