# Zero-Shot Learning via Class-Conditioned Deep Generative Models

arXiv: https://arxiv.org/abs/1711.05820 · HTML: https://mlsanity.com/paper/1711.05820/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Nov 2017.

## Built on by (most cited first, 21 of 21)

- [Exploiting a Joint Embedding Space for Generalized Zero-Shot Semantic Segmentation](https://mlsanity.com/paper/2108.06536/) (2021)
- [Zero-Shot Learning by Harnessing Adversarial Samples](https://mlsanity.com/paper/2308.00313/) (2023)
- [Towards Novel Target Discovery Through Open-Set Domain Adaptation](https://mlsanity.com/paper/2105.02432/) (2021)
- [Text-centric Alignment for Multi-Modality Learning](https://mlsanity.com/paper/2402.08086/) (2024)
- [Attribute-Modulated Generative Meta Learning for Zero-Shot Classification](https://mlsanity.com/paper/2104.10857/) (2021)
- [Boosting Generative Zero-Shot Learning by Synthesizing Diverse Features with Attribute Augmentation](https://mlsanity.com/paper/2112.12573/) (2021)
- [Zero-shot-Learning Cross-Modality Data Translation Through Mutual Information Guided Stochastic Diffusion](https://mlsanity.com/paper/2301.13743/) (2023)
- [SVIP: Semantically Contextualized Visual Patches for Zero-Shot Learning](https://mlsanity.com/paper/2503.10252/) (2025)
- [Dynamic VAEs with Generative Replay for Continual Zero-shot Learning](https://mlsanity.com/paper/2104.12468/) (2021)
- [Learning Aligned Cross-Modal Representation for Generalized Zero-Shot Classification](https://mlsanity.com/paper/2112.12927/) (2021)
- [Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learning](https://mlsanity.com/paper/2201.01961/) (2022)
- [Adapt and Align to Improve Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2305.05144/) (2023)
- [An Integral Projection-based Semantic Autoencoder for Zero-Shot Learning](https://mlsanity.com/paper/2306.14628/) (2023)
- [Bias-Eliminated Semantic Refinement for Any-Shot Learning](https://mlsanity.com/paper/2202.04827/) (2022)
- [Generate, Transduct, Adapt: Iterative Transduction with VLMs](https://mlsanity.com/paper/2501.06031/) (2025)
- [MetaFBP: Learning to Learn High-Order Predictor for Personalized Facial Beauty Prediction](https://mlsanity.com/paper/2311.13929/) (2023)
- [Class Knowledge Overlay to Visual Feature Learning for Zero-Shot Image Classification](https://mlsanity.com/paper/2102.13322/) (2021)
- [Targeted Attention for Generalized- and Zero-Shot Learning](https://mlsanity.com/paper/2211.09322/) (2022)
- [A Systematic Evaluation and Benchmark for Embedding-Aware Generative Models: Features, Models, and Any-shot Scenarios](https://mlsanity.com/paper/2302.04060/) (2023)
- [High-Discriminative Attribute Feature Learning for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2404.04953/) (2024)
- [Will It Zero-Shot?: Predicting Zero-Shot Classification Performance For Arbitrary Queries](https://mlsanity.com/paper/2601.17535/) (2026)

## Abstract (arXiv)

We present a deep generative model for learning to predict classes not seen at training time. Unlike most existing methods for this problem, that represent each class as a point (via a semantic embedding), we represent each seen/unseen class using a class-specific latent-space distribution, conditioned on class attributes. We use these latent-space distributions as a prior for a supervised variational autoencoder (VAE), which also facilitates learning highly discriminative feature representations for the inputs. The entire framework is learned end-to-end using only the seen-class training data. The model infers corresponding attributes of a test image by maximizing the VAE lower bound; the inferred attributes may be linked to labels not seen when training. We further extend our model to a (1) semi-supervised/transductive setting by leveraging unlabeled unseen-class data via an unsupervised learning module, and (2) few-shot learning where we also have a small number of labeled inputs from the unseen classes. We compare our model with several state-of-the-art methods through a comprehensive set of experiments on a variety of benchmark data sets.