# Leveraging the Invariant Side of Generative Zero-Shot Learning

arXiv: https://arxiv.org/abs/1904.04092 · HTML: https://mlsanity.com/paper/1904.04092/

## Key facts

- Cited by 83 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Apr 2019.

## Built on by (most cited first, 30 of 83)

- [Counterfactual Zero-Shot and Open-Set Visual Recognition](https://mlsanity.com/paper/2103.00887/) (2021)
- [Contrastive Embedding for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.16173/) (2021)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learning](https://mlsanity.com/paper/2109.15163/) (2021)
- [Semantics Disentangling for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.07978/) (2021)
- [Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.06536/) (2021)
- [Improving Zero-Shot Generalization for CLIP with Synthesized Prompts](https://mlsanity.com/paper/2307.07397/) (2023)
- [MSDN: Mutually Semantic Distillation Network for Zero-Shot Learning](https://mlsanity.com/paper/2203.03137/) (2022)
- [OntoZSL: Ontology-enhanced Zero-shot Learning](https://mlsanity.com/paper/2102.07339/) (2021)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Fine-Grained Zero-Shot Learning with DNA as Side Information](https://mlsanity.com/paper/2109.14133/) (2021)
- [Generative Multi-Label Zero-Shot Learning](https://mlsanity.com/paper/2101.11606/) (2021)
- [Attribute Prototype Network for Any-Shot Learning](https://mlsanity.com/paper/2204.01208/) (2022)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Mitigating Generation Shifts for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.03163/) (2021)
- [Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning](https://mlsanity.com/paper/2106.00264/) (2021)
- [GSMFlow: Generation Shifts Mitigating Flow for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2207.01798/) (2022)
- [Non-generative Generalized Zero-shot Learning via Task-correlated Disentanglement and Controllable Samples Synthesis](https://mlsanity.com/paper/2203.05335/) (2022)
- [Learning Adversarial Semantic Embeddings for Zero-Shot Recognition in Open Worlds](https://mlsanity.com/paper/2307.03416/) (2023)
- [Towards Visual Explainable Active Learning for Zero-Shot Classification](https://mlsanity.com/paper/2108.06730/) (2021)
- [Entropy-Based Uncertainty Calibration for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2101.03292/) (2021)
- [Boosting Zero-shot Learning via Contrastive Optimization of Attribute Representations](https://mlsanity.com/paper/2207.03824/) (2022)
- [Data-Free Generalized Zero-Shot Learning](https://mlsanity.com/paper/2401.15657/) (2024)
- [Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation](https://mlsanity.com/paper/2112.12573/) (2021)
- [Semantic Feature Extraction for Generalized Zero-shot Learning](https://mlsanity.com/paper/2112.14478/) (2021)
- [A Survey on Visual Transfer Learning using Knowledge Graphs](https://mlsanity.com/paper/2201.11794/) (2022)
- [Unseen Classes at a Later Time? No Problem](https://mlsanity.com/paper/2203.16517/) (2022)
- [Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2302.00875/) (2023)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [Generalizing vision-language models to novel domains: A comprehensive survey](https://mlsanity.com/paper/2506.18504/) (2025)

## Abstract (arXiv)

Conventional zero-shot learning (ZSL) methods generally learn an embedding, e.g., visual-semantic mapping, to handle the unseen visual samples via an indirect manner. In this paper, we take the advantage of generative adversarial networks (GANs) and propose a novel method, named leveraging invariant side GAN (LisGAN), which can directly generate the unseen features from random noises which are conditioned by the semantic descriptions. Specifically, we train a conditional Wasserstein GANs in which the generator synthesizes fake unseen features from noises and the discriminator distinguishes the fake from real via a minimax game. Considering that one semantic description can correspond to various synthesized visual samples, and the semantic description, figuratively, is the soul of the generated features, we introduce soul samples as the invariant side of generative zero-shot learning in this paper. A soul sample is the meta-representation of one class. It visualizes the most semantically-meaningful aspects of each sample in the same category. We regularize that each generated sample (the varying side of generative ZSL) should be close to at least one soul sample (the invariant side) which has the same class label with it. At the zero-shot recognition stage, we propose to use two classifiers, which are deployed in a cascade way, to achieve a coarse-to-fine result. Experiments on five popular benchmarks verify that our proposed approach can outperform state-of-the-art methods with significant improvements.