Type
ArticleKAUST Department
Computer Science ProgramComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Machine Intelligence & kNowledge Engineering Lab
Date
2020-09-21Online Publication Date
2020-09-21Print Publication Date
2020-12Embargo End Date
2022-09-22Submitted Date
2020-06-19Permanent link to this record
http://hdl.handle.net/10754/665385
Metadata
Show full item recordAbstract
The goal of zero-shot learning (ZSL) is to build a classifier that recognizes novel categories with no corresponding annotated training data. The typical routine is to transfer knowledge from seen classes to unseen ones by learning a visual-semantic embedding. Existing multi-label zero-shot learning approaches either ignore correlations among labels, suffer from large label combinations, or learn the embedding using only local or global visual features. In this paper, we propose a Graph Convolution Networks based Multi-label Zero-Shot Learning model, abbreviated as MZSL-GCN. Our model first constructs a label relation graph using label co-occurrences and compensates the absence of unseen labels in the training phase by semantic similarity. It then takes the graph and the word embedding of each seen (unseen) label as inputs to the GCN to learn the label semantic embedding, and to obtain a set of inter-dependent object classifiers. MZSL-GCN simultaneously trains another attention network to learn compatible local and global visual features of objects with respect to the classifiers, and thus makes the whole network end-to-end trainable. In addition, the use of unlabeled training data can reduce the bias toward seen labels and boost the generalization ability. Experimental results on benchmark datasets show that our MZSL-GCN competes with state-of-the-art approaches.Citation
Ou, G., Yu, G., Domeniconi, C., Lu, X., & Zhang, X. (2020). Multi-label zero-shot learning with graph convolutional networks. Neural Networks, 132, 333–341. doi:10.1016/j.neunet.2020.09.010Sponsors
This work was supported by National Natural Science Foundation of China (62031003, 61872300 and 62072380).Publisher
Elsevier BVJournal
Neural NetworksPubMed ID
32977278Additional Links
https://linkinghub.elsevier.com/retrieve/pii/S0893608020303336ae974a485f413a2113503eed53cd6c53
10.1016/j.neunet.2020.09.010
Scopus Count
Related articles
- Multi-label zero-shot human action recognition via joint latent ranking embedding.
- Authors: Wang Q, Chen K
- Issue date: 2020 Feb
- Knowledge-Guided Multi-Label Few-Shot Learning for General Image Recognition.
- Authors: Chen T, Lin L, Chen R, Hui X, Wu H
- Issue date: 2022 Mar
- Visual-guided attentive attributes embedding for zero-shot learning.
- Authors: Zhang R, Zhu Q, Xu X, Zhang D, Huang SJ
- Issue date: 2021 Nov
- Augmented semantic feature based generative network for generalized zero-shot learning.
- Authors: Li Z, Chen Q, Liu Q
- Issue date: 2021 Nov
- Label-activating framework for zero-shot learning.
- Authors: Liu Y, Gao X, Gao Q, Han J, Shao L
- Issue date: 2020 Jan