# Towards Zero-Shot Learning with Fewer Seen Class Examples

arXiv: https://arxiv.org/abs/2011.07279 · HTML: https://mlsanity.com/paper/2011.07279/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2020.

## Built on by (most cited first, 4 of 4)

- [What Can Knowledge Bring to Machine Learning? -- A Survey of Low-shot Learning for Structured Data](https://mlsanity.com/paper/2106.06410/) (2021)
- [Probabilistic Embeddings for Frozen Vision-Language Models: Uncertainty Quantification with Gaussian Process Latent Variable Models](https://mlsanity.com/paper/2505.05163/) (2025)
- [Generative Replay-based Continual Zero-Shot Learning](https://mlsanity.com/paper/2101.08894/) (2021)
- [Meta-Learned Attribute Self-Gating for Continual Generalized Zero-Shot Learning](https://mlsanity.com/paper/2102.11856/) (2021)

## Abstract (arXiv)

We present a meta-learning based generative model for zero-shot learning (ZSL) towards a challenging setting when the number of training examples from each seen class is very few. This setup contrasts with the conventional ZSL approaches, where training typically assumes the availability of a sufficiently large number of training examples from each of the seen classes. The proposed approach leverages meta-learning to train a deep generative model that integrates variational autoencoder and generative adversarial networks. We propose a novel task distribution where meta-train and meta-validation classes are disjoint to simulate the ZSL behaviour in training. Once trained, the model can generate synthetic examples from seen and unseen classes. Synthesize samples can then be used to train the ZSL framework in a supervised manner. The meta-learner enables our model to generates high-fidelity samples using only a small number of training examples from seen classes. We conduct extensive experiments and ablation studies on four benchmark datasets of ZSL and observe that the proposed model outperforms state-of-the-art approaches by a significant margin when the number of examples per seen class is very small.