Transfer feature generating networks with semantic classes structure for zero-shot learning

Abstract

Feature generating networks face to the most important question, which is the fitting difference (inconsistence) of the distribution between the generated feature and the real data. This inconsistence further influence the performance of the networks model, because training samples from seen classes is disjointed with testing samples from unseen classes in zero-shot learning (ZSL). In generalization zero-shot learning (GZSL), testing samples come from not only seen classes but also unseen classes for closer to the practical situation. Therefore, most of feature generating networks difficultly obtain satisfactory performance for the challenging GZSL by adversarial learning the distribution of semantic classes. To alleviate the negative influence of this inconsistence for ZSL and GZSL, transfer feature generating networks with semantic classes structure (TFGNSCS) is proposed to construct networks model for improving the performance of ZSL and GZSL. TFGNSCS can not only consider the semantic structure relationship between seen and unseen classes, but also learn the difference of generating features by transferring classification model information from seen to unseen classes in networks. The proposed method can integrate the transfer loss, the classification loss and the Wasserstein distance loss to generate enough CNN features, on which softmax classifiers are trained for ZSL and GZSL. Experiments demonstrate that the performance of TFGNSCS outperforms that of the state of the arts on four challenging datasets, which are CUB,FLO,SUN, AWA in GZSL.

References in corpus (12)

• Conditional Generative Adversarial Nets
• Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Zero-Shot Learning Through Cross-Modal Transfer
• Label-Embedding for Image Classification
• Zero-Shot Learning by Convex Combination of Semantic Embeddings
• Evaluation of Output Embeddings for Fine-Grained Image Classification
• Transductive Multi-view Zero-Shot Learning
• Transductive Zero-Shot Learning with Visual Structure Constraint
• Transductive Unbiased Embedding for Zero-Shot Learning
• Structure propagation for zero-shot learning
• Class label autoencoder for zero-shot learning

Cited by in corpus (2)

• A Review of Generalized Zero-Shot Learning Methods
• Structure fusion based on graph convolutional networks for semi-supervised classification