Predicting Visual Exemplars of Unseen Classes for Zero-Shot Learning

2016/05/26 by Soravit Changpinyo, Changpinyo, Soravit, Wei‐Lun Chao +3 · 2 citations
Computer Science · Medicine · #COVID-19 diagnosis using AI #Computer Vision and Pattern Recognition (cs.CV) #Domain Adaptation and Few-Shot Learning #FOS: Computer and information sciences #Multimodal Machine Learning Applications

paper · pdf · doi:10.48550/arxiv.1605.08151

openalex publication_date 2016/05/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Citations

• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Predicting Deep Zero-Shot Convolutional Neural Networks using Textual Descriptions
• Zero-Shot Learning via Semantic Similarity Embedding
• ImageNet Large Scale Visual Recognition Challenge
• Attribute2Image: Conditional Image Generation from Visual Attributes
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• Zero-Shot Visual Recognition via Bidirectional Latent Embedding

Cited by

• Visual Distribution Anchoring for Efficient Prompt Tuning
• Zero-Shot Sketch-Image Hashing

Related

• Synthesized Classifiers for Zero-Shot Learning
• Classifier and Exemplar Synthesis for Zero-Shot Learning
• Semi-supervised Zero-Shot Learning by a Clustering-based Approach
• Generalized Zero-Shot Recognition based on Visually Semantic Embedding
• Learning Robust Visual-semantic Mapping for Zero-shot Learning