# SR-GAN: Semantic Rectifying Generative Adversarial Network for Zero-shot Learning

arXiv: https://arxiv.org/abs/1904.06996 · HTML: https://mlsanity.com/paper/1904.06996/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Apr 2019.

## Built on by (most cited first, 6 of 6)

- [Physics-Informed Computer Vision: A Review and Perspectives](https://mlsanity.com/paper/2305.18035/) (2023)
- [Disentangling Semantic-to-visual Confusion for Zero-shot Learning](https://mlsanity.com/paper/2106.08605/) (2021)
- [Rebalanced Zero-shot Learning](https://mlsanity.com/paper/2210.07031/) (2022)
- [Data-Free Generalized Zero-Shot Learning](https://mlsanity.com/paper/2401.15657/) (2024)
- [AH-GS: Augmented 3D Gaussian Splatting for High-Frequency Detail Representation](https://mlsanity.com/paper/2503.22324/) (2025)
- [Adversarial Robustness in Zero-Shot Learning:An Empirical Study on Class and Concept-Level Vulnerabilities](https://mlsanity.com/paper/2512.18651/) (2025)

## Abstract (arXiv)

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.