Semi-supervised Zero-Shot Learning by a Clustering-based Approach

Abstract

In some of object recognition problems, labeled data may not be available for all categories. Zero-shot learning utilizes auxiliary information (also called signatures) describing each category in order to find a classifier that can recognize samples from categories with no labeled instance. In this paper, we propose a novel semi-supervised zero-shot learning method that works on an embedding space corresponding to abstract deep visual features. We seek a linear transformation on signatures to map them onto the visual features, such that the mapped signatures of the seen classes are close to labeled samples of the corresponding classes and unlabeled data are also close to the mapped signatures of one of the unseen classes. We use the idea that the rich deep visual features provide a representation space in which samples of each class are usually condensed in a cluster. The effectiveness of the proposed method is demonstrated through extensive experiments on four public benchmarks improving the state-of-the-art prediction accuracy on three of them.

8 pages

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Scikit-learn: Machine Learning in Python
• 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
• Latent Embeddings for Zero-shot Classification
• Semi-supervised Vocabulary-informed Learning
• Multi-Cue Zero-Shot Learning with Strong Supervision
• Zero-Shot Learning via Joint Latent Similarity Embedding
• Less is more: zero-shot learning from online textual documents with noise suppression

Cited by in corpus (10)

• Small Sample Learning in Big Data Era
• Weak-shot Fine-grained Classification via Similarity Transfer
• Transductive Zero-Shot Learning with a Self-training dictionary approach
• Zero and Few Shot Learning with Semantic Feature Synthesis and Competitive Learning
• Zero-Shot Learning via Category-Specific Visual-Semantic Mapping
• Joint Concept Matching based Learning for Zero-Shot Recognition
• Fine-grained Classification using Heterogeneous Web Data and Auxiliary Categories
• Zero-Shot Recognition via Optimal Transport
• SDM-Net: A Simple and Effective Model for Generalized Zero-Shot Learning
• Zero-Shot Learning with Sparse Attribute Propagation