1. Graph-Based Visual-Semantic Entanglement Network for Zero-Shot Image Recognition
- Author
-
Wendy Hall, Yang Hu, Dan Dai, Pei Yang, Mingnan Luo, Yingxue Xu, Adriane Chapman, and Guihua Wen
- Subjects
FOS: Computer and information sciences ,Computer Science - Machine Learning ,Computer science ,Computer Vision and Pattern Recognition (cs.CV) ,media_common.quotation_subject ,Computer Science - Computer Vision and Pattern Recognition ,Space (commercial competition) ,Convolutional neural network ,Machine Learning (cs.LG) ,FOS: Electrical engineering, electronic engineering, information engineering ,Media Technology ,Electrical and Electronic Engineering ,Representation (mathematics) ,media_common ,business.industry ,Image and Video Processing (eess.IV) ,Pattern recognition ,Ambiguity ,Electrical Engineering and Systems Science - Image and Video Processing ,Computer Science Applications ,Signal Processing ,Graph (abstract data type) ,Embedding ,Visual modeling ,Artificial intelligence ,business ,Word (computer architecture) - Abstract
Zero-shot learning uses semantic attributes to connect the search space of unseen objects. In recent years, although the deep convolutional network brings powerful visual modeling capabilities to the ZSL task, its visual features have severe pattern inertia and lack of representation of semantic relationships, which leads to severe bias and ambiguity. In response to this, we propose the Graph-based Visual-Semantic Entanglement Network to conduct graph modeling of visual features, which is mapped to semantic attributes by using a knowledge graph, it contains several novel designs: 1. it establishes a multi-path entangled network with the convolutional neural network (CNN) and the graph convolutional network (GCN), which input the visual features from CNN to GCN to model the implicit semantic relations, then GCN feedback the graph modeled information to CNN features; 2. it uses attribute word vectors as the target for the graph semantic modeling of GCN, which forms a self-consistent regression for graph modeling and supervise GCN to learn more personalized attribute relations; 3. it fuses and supplements the hierarchical visual-semantic features refined by graph modeling into visual embedding. Our method outperforms state-of-the-art approaches on multiple representative ZSL datasets: AwA2, CUB, and SUN by promoting the semantic linkage modelling of visual features., 15 pages, 11 figures, on IEEE Transactions on Multimedia
- Published
- 2022