SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning
This addresses the challenge of improving discrimination among classes in ZSL, which is crucial for applications like image recognition with limited labeled data, though it appears incremental as it builds on existing GAN-based methods.
The paper tackles the problem of vague and overlapping class attributes in Zero-Shot Learning (ZSL) by proposing SR-GAN, which rectifies the semantic space using visual guidance and generates visual features for unseen classes, achieving state-of-the-art results on four benchmark datasets.
The existing Zero-Shot learning (ZSL) methods may suffer from the vague class attributes that are highly overlapped for different classes. Unlike these methods that ignore the discrimination among classes, in this paper, we propose to classify unseen image by rectifying the semantic space guided by the visual space. First, we pre-train a Semantic Rectifying Network (SRN) to rectify semantic space with a semantic loss and a rectifying loss. Then, a Semantic Rectifying Generative Adversarial Network (SR-GAN) is built to generate plausible visual feature of unseen class from both semantic feature and rectified semantic feature. To guarantee the effectiveness of rectified semantic features and synthetic visual features, a pre-reconstruction and a post reconstruction networks are proposed, which keep the consistency between visual feature and semantic feature. Experimental results demonstrate that our approach significantly outperforms the state-of-the-arts on four benchmark datasets.