Synthesized Classifiers for Zero-Shot Learning

Abstract

Given semantic descriptions of object classes, zero-shot learning aims to accurately recognize objects of the unseen classes, from which no examples are available at the training stage, by associating them to the seen classes, from which labeled examples are provided. We propose to tackle this problem from the perspective of manifold learning. Our main idea is to align the semantic space that is derived from external information to the model space that concerns itself with recognizing visual features. To this end, we introduce a set of "phantom" object classes whose coordinates live in both the semantic space and the model space. Serving as bases in a dictionary, they can be optimized from labeled data such that the synthesized real object classifiers achieve optimal discriminative performance. We demonstrate superior accuracy of our approach over the state of the art on four benchmark datasets for zero-shot learning, including the full ImageNet Fall 2011 dataset with more than 20,000 unseen classes.

References in corpus (7)

• Efficient Estimation of Word Representations in Vector Space
• Caffe: Convolutional Architecture for Fast Feature Embedding
• OverFeat: Integrated Recognition, Localization and Detection using Convolutional Networks
• Transductive Multi-view Zero-Shot Learning
• Zero-Shot Learning via Semantic Similarity Embedding
• Unsupervised Learning on Neural Network Outputs: with Application in Zero-shot Learning
• Zero-Shot Learning via Joint Latent Similarity Embedding

Cited by in corpus (13)

• Zero-Shot Learning -- The Good, the Bad and the Ugly
• An Empirical Study and Analysis of Generalized Zero-Shot Learning for Object Recognition in the Wild
• Transductive Zero-Shot Learning with Visual Structure Constraint
• Learning the Redundancy-free Features for Generalized Zero-Shot Object Recognition
• Zero-Shot Visual Recognition via Bidirectional Latent Embedding
• Zero-Shot Semantic Segmentation
• Classifier and Exemplar Synthesis for Zero-Shot Learning
• Bi-Semantic Reconstructing Generative Network for Zero-shot Learning
• Weak Novel Categories without Tears: A Survey on Weak-Shot Learning
• OntoZSL: Ontology-enhanced Zero-shot Learning
• DFS: A Diverse Feature Synthesis Model for Generalized Zero-Shot Learning
• Learning Clusterable Visual Features for Zero-Shot Recognition
• Zero-Shot Learning from Adversarial Feature Residual to Compact Visual Feature