# Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning

arXiv: https://arxiv.org/abs/1605.08151 · HTML: https://mlsanity.com/paper/1605.08151/

## Key facts

- Cited by 30 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 May 2016.

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

- [DetCLIP: Dictionary-Enriched Visual-Concept Paralleled Pre-training for Open-world Detection](https://mlsanity.com/paper/2209.09407/) (2022)
- [K-LITE: Learning Transferable Visual Models with External Knowledge](https://mlsanity.com/paper/2204.09222/) (2022)
- [FREE: Feature Refinement for Generalized Zero-Shot Learning](https://mlsanity.com/paper/2107.13807/) (2021)
- [TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learning](https://mlsanity.com/paper/2112.08643/) (2021)
- [Isometric Propagation Network for Generalized Zero-shot Learning](https://mlsanity.com/paper/2102.02038/) (2021)
- [Learning Robust Visual-semantic Mapping for Zero-shot Learning](https://mlsanity.com/paper/2104.05668/) (2021)
- [On Bridging Generic and Personalized Federated Learning for Image Classification](https://mlsanity.com/paper/2107.00778/) (2021)
- [Hardness Sampling for Self-Training Based Transductive Zero-Shot Learning](https://mlsanity.com/paper/2106.00264/) (2021)
- [Towards Visual Explainable Active Learning for Zero-Shot Classification](https://mlsanity.com/paper/2108.06730/) (2021)
- [Revisiting Document Representations for Large-Scale Zero-Shot Learning](https://mlsanity.com/paper/2104.10355/) (2021)
- [Bi-directional Distribution Alignment for Transductive Zero-Shot Learning](https://mlsanity.com/paper/2303.08698/) (2023)
- [Region Semantically Aligned Network for Zero-Shot Learning](https://mlsanity.com/paper/2110.07130/) (2021)
- [Recognize Any Regions](https://mlsanity.com/paper/2311.01373/) (2023)
- [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)
- [Open-Vocabulary Federated Learning with Multimodal Prototyping](https://mlsanity.com/paper/2404.01232/) (2024)
- [Multi-Domain Few-Shot Learning and Dataset for Agricultural Applications](https://mlsanity.com/paper/2109.09952/) (2021)
- [An Iterative Co-Training Transductive Framework for Zero Shot Learning](https://mlsanity.com/paper/2203.16041/) (2022)
- [PSVMA+: Exploring Multi-granularity Semantic-visual Adaption for Generalized Zero-shot Learning](https://mlsanity.com/paper/2410.11560/) (2024)
- [GAN for Vision, KG for Relation: a Two-stage Deep Network for Zero-shot Action Recognition](https://mlsanity.com/paper/2105.11789/) (2021)
- [HardBoost: Boosting Zero-Shot Learning with Hard Classes](https://mlsanity.com/paper/2201.05479/) (2022)
- [Semantic Enhanced Knowledge Graph for Large-Scale Zero-Shot Learning](https://mlsanity.com/paper/2212.13151/) (2022)
- [Semantic-diversity transfer network for generalized zero-shot learning via inner disagreement based OOD detector](https://mlsanity.com/paper/2203.09017/) (2022)
- [Text2Model: Text-based Model Induction for Zero-shot Image Classification](https://mlsanity.com/paper/2210.15182/) (2022)
- [Unsupervised Brain Tumor Segmentation with Image-based Prompts](https://mlsanity.com/paper/2304.01472/) (2023)
- [Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation](https://mlsanity.com/paper/2306.08487/) (2023)
- [WAD-CMSN: Wasserstein Distance based Cross-Modal Semantic Network for Zero-Shot Sketch-Based Image Retrieval](https://mlsanity.com/paper/2202.05465/) (2022)
- [Tight Lower Bounds on Worst-Case Guarantees for Zero-Shot Learning with Attributes](https://mlsanity.com/paper/2205.13068/) (2022)
- [A Zero-shot Learning Method Based on Large Language Models for Multi-modal Knowledge Graph Embedding](https://mlsanity.com/paper/2503.07202/) (2025)
- [Visual Distribution Anchoring for Efficient Prompt Tuning](https://mlsanity.com/paper/2607.28967/) (2026)

## Abstract (arXiv)

Leveraging class semantic descriptions and examples of known objects, zero-shot learning makes it possible to train a recognition model for an object class whose examples are not available. In this paper, we propose a novel zero-shot learning model that takes advantage of clustering structures in the semantic embedding space. The key idea is to impose the structural constraint that semantic representations must be predictive of the locations of their corresponding visual exemplars. To this end, this reduces to training multiple kernel-based regressors from semantic representation-exemplar pairs from labeled data of the seen object categories. Despite its simplicity, our approach significantly outperforms existing zero-shot learning methods on standard benchmark datasets, including the ImageNet dataset with more than 20,000 unseen categories.