# A Generative Framework for Zero-Shot Learning with Adversarial Domain Adaptation

arXiv: https://arxiv.org/abs/1906.03038 · HTML: https://mlsanity.com/paper/1906.03038/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Jun 2019.

## Built on by (most cited first, 8 of 8)

- [Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning](https://mlsanity.com/paper/2106.00264/) (2021)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.01167/) (2023)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [Prompt-guided Scene Generation for 3D Zero-Shot Learning](https://mlsanity.com/paper/2209.14690/) (2022)
- [Zero-Shot Visual Deepfake Detection: Can AI Predict and Prevent Fake Content Before It's Created?](https://mlsanity.com/paper/2509.18461/) (2025)
- [A Simple Approach for Zero-Shot Learning based on Triplet Distribution Embeddings](https://mlsanity.com/paper/2103.15939/) (2021)
- [Zero-sample surface defect detection and classification based on semantic feedback neural network](https://mlsanity.com/paper/2106.07959/) (2021)

## Abstract (arXiv)

We present a domain adaptation based generative framework for zero-shot learning. Our framework addresses the problem of domain shift between the seen and unseen class distributions in zero-shot learning and minimizes the shift by developing a generative model trained via adversarial domain adaptation. Our approach is based on end-to-end learning of the class distributions of seen classes and unseen classes. To enable the model to learn the class distributions of unseen classes, we parameterize these class distributions in terms of the class attribute information (which is available for both seen and unseen classes). This provides a very simple way to learn the class distribution of any unseen class, given only its class attribute information, and no labeled training data. Training this model with adversarial domain adaptation further provides robustness against the distribution mismatch between the data from seen and unseen classes. Our approach also provides a novel way for training neural net based classifiers to overcome the hubness problem in zero-shot learning. Through a comprehensive set of experiments, we show that our model yields superior accuracies as compared to various state-of-the-art zero shot learning models, on a variety of benchmark datasets. Code for the experiments is available at github.com/vkkhare/ZSL-ADA