Transfer Feature Generating Networks With Semantic Classes Structure for Zero-Shot Learning

@article{Lin2019TransferFG,
  title={Transfer Feature Generating Networks With Semantic Classes Structure for Zero-Shot Learning},
  author={Guangfeng Lin and Wanjun Chen and Kaiyang Liao and Xiaobing Kang and Caixia Fan},
  journal={IEEE Access},
  year={2019},
  volume={7},
  pages={176470-176483}
}
Feature generating networks face a very important issue, which is the fitting difference (inconsistency) of the distribution between the generated feature and the real data. [...] Key Method TFGNSCS not only can consider the semantic structure relationship between seen and unseen classes, but also can learn the difference of generating features by transferring classification model information from seen to unseen classes in networks.Expand
Generalized Zero Shot Learning via Synthesis Pseudo Features
TLDR
This work proposes a GZSL method that transforms GZ SL problems to conventional supervised learning ones by synthesizing pseudo features for unseen classes contrary to current synthesis-based methods, which synthesize pseudo instances. Expand
Structure fusion based on graph convolutional networks for semi-supervised classification
TLDR
The proposed structure fusion based on graph convolutional networks (SPF-GCN) outperforms that of the state-of-the-art methods on three challenging datasets, which are Cora, Citeseer, and Pubmed in citation networks. Expand
Structure Fusion Based on Graph Convolutional Networks for Node Classification in Citation Networks
TLDR
The proposed structure fusion based on graph convolutional networks (SPF-GCN) outperforms that of the state-of-the-art methods on three challenging datasets, which are Cora, Citeseer, and Pubmed in citation networks. Expand
A Review of Generalized Zero-Shot Learning Methods
TLDR
This review paper presents a hierarchical categorization of the GZSL methods and discusses the representative methods of each category, and discusses several research directions for future studies. Expand

References

SHOWING 1-10 OF 72 REFERENCES
Feature Generating Networks for Zero-Shot Learning
TLDR
A novel generative adversarial network (GAN) that synthesizes CNN features conditioned on class-level semantic information, offering a shortcut directly from a semantic descriptor of a class to a class-conditional feature distribution. Expand
Class label autoencoder for zero-shot learning
TLDR
A novel method to ZSL based on learning class label autoencoder (CLA), which can not only build a uniform framework for adapting to multi-semantic embedding spaces, but also construct the encoder-decoder mechanism for constraining the bidirectional projection between the feature space and the class label space. Expand
Gradient Matching Generative Networks for Zero-Shot Learning
TLDR
This work proposes a generative model that can naturally learn from unsupervised examples, and synthesize training examples for unseen classes purely based on their class embeddings, and therefore, reduce the zero-shot learning problem into a supervised classification task. Expand
Structure Fusion and Propagation for Zero-Shot Learning
The key of zero-shot learning (ZSL) is how to find the information transfer model for bridging the gap between images and semantic information (texts or attributes). Existing ZSL methods usuallyExpand
Transductive Zero-Shot Learning with Visual Structure Constraint
TLDR
This work proposes a new visual structure constraint on class centers for transductive ZSL, to improve the generality of the projection function and alleviate the above domain shift problem. Expand
Adversarial unseen visual feature synthesis for Zero-shot Learning
TLDR
Qualitative results show that the proposed hybrid model consists of Random Attribute Selection (RAS) and conditional Generative Adversarial Network (cGAN) can capture more realistic distribution and remarkably improve the variability of the synthesized data. Expand
F-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learning
TLDR
A conditional generative model that combines the strength of VAE and GANs and in addition, via an unconditional discriminator, learns the marginal feature distribution of unlabeled images is developed. Expand
Semantic Autoencoder for Zero-Shot Learning
TLDR
This work presents a novel solution to ZSL based on learning a Semantic AutoEncoder (SAE), which outperforms significantly the existing ZSL models with the additional benefit of lower computational cost and beats the state-of-the-art when the SAE is applied to supervised clustering problem. Expand
Zero-Shot Learning via Semantic Similarity Embedding
In this paper we consider a version of the zero-shot learning problem where seen class source and target domain data are provided. The goal during test-time is to accurately predict the class labelExpand
Transductive Unbiased Embedding for Zero-Shot Learning
TLDR
This paper proposes a straightforward yet effective method named Quasi-Fully Supervised Learning (QFSL) to alleviate the bias problem in Zero-Shot Learning, which outperforms existing state-of-the-art approaches by a huge margin. Expand
...
1
2
3
4
5
...