# A Simple Exponential Family Framework for Zero-Shot Learning

arXiv: https://arxiv.org/abs/1707.08040 · HTML: https://mlsanity.com/paper/1707.08040/

## Key facts

- Cited by 38 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2017.

## Built on by (most cited first, 30 of 38)

- [A Closer Look at Self-training for Zero-Label Semantic Segmentation](https://mlsanity.com/paper/2104.11692/) (2021)
- [Zero-Shot Learning on 3D Point Cloud Objects and Beyond](https://mlsanity.com/paper/2104.04980/) (2021)
- [Task Aligned Generative Meta-learning for Zero-shot Learning](https://mlsanity.com/paper/2103.02185/) (2021)
- [Learning Robust Visual-semantic Mapping for Zero-shot Learning](https://mlsanity.com/paper/2104.05668/) (2021)
- [Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning](https://mlsanity.com/paper/2106.00264/) (2021)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)
- [Generative Replay-based Continual Zero-Shot Learning](https://mlsanity.com/paper/2101.08894/) (2021)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [Adversarial Training of Variational Auto-encoders for Continual Zero-shot Learning(A-CZSL)](https://mlsanity.com/paper/2102.03778/) (2021)
- [Dynamic VAEs with Generative Replay for Continual Zero-shot Learning](https://mlsanity.com/paper/2104.12468/) (2021)
- [Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learning](https://mlsanity.com/paper/2112.00410/) (2021)
- [Field-Guide-Inspired Zero-Shot Learning](https://mlsanity.com/paper/2108.10967/) (2021)
- [Semantically Grounded Visual Embeddings for Zero-Shot Learning](https://mlsanity.com/paper/2201.00577/) (2022)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [Vocabulary-informed Zero-shot and Open-set Learning](https://mlsanity.com/paper/2301.00998/) (2023)
- [A Comprehensive Review and a Taxonomy of Edge Machine Learning: Requirements, Paradigms, and Techniques](https://mlsanity.com/paper/2302.08571/) (2023)
- [Online Lifelong Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.10741/) (2021)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/2306.14628/) (2023)
- [Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning](https://mlsanity.com/paper/2312.01167/) (2023)
- [Learning Semantic Ambiguities for Zero-Shot Learning](https://mlsanity.com/paper/2201.01823/) (2022)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [Bias-Eliminated Semantic Refinement for Any-Shot Learning](https://mlsanity.com/paper/2202.04827/) (2022)
- [Prompt-guided Scene Generation for 3D Zero-Shot Learning](https://mlsanity.com/paper/2209.14690/) (2022)
- [Efficient Gaussian Process Model on Class-Imbalanced Datasets for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2210.06120/) (2022)
- [Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning](https://mlsanity.com/paper/2212.13151/) (2022)
- [Zero-shot Learning with Deep Neural Networks for Object Recognition](https://mlsanity.com/paper/2102.03137/) (2021)
- [Transductive Zero-Shot Learning by Decoupled Feature Generation](https://mlsanity.com/paper/2102.03266/) (2021)
- [Learn from Anywhere: Rethinking Generalized Zero-Shot Learning with Limited Supervision](https://mlsanity.com/paper/2107.04952/) (2021)
- [DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2103.10764/) (2021)

## Abstract (arXiv)

We present a simple generative framework for learning to predict previously unseen classes, based on estimating class-attribute-gated class-conditional distributions. We model each class-conditional distribution as an exponential family distribution and the parameters of the distribution of each seen/unseen class are defined as functions of the respective observed class attributes. These functions can be learned using only the seen class data and can be used to predict the parameters of the class-conditional distribution of each unseen class. Unlike most existing methods for zero-shot learning that represent classes as fixed embeddings in some vector space, our generative model naturally represents each class as a probability distribution. It is simple to implement and also allows leveraging additional unlabeled data from unseen classes to improve the estimates of their class-conditional distributions using transductive/semi-supervised learning. Moreover, it extends seamlessly to few-shot learning by easily updating these distributions when provided with a small number of additional labelled examples from unseen classes. Through a comprehensive set of experiments on several benchmark data sets, we demonstrate the efficacy of our framework.