Semantic Graph-enhanced Visual Network for Zero-shot Learning Article Swipe

MAKE IMPACT

Yang Hu , Guihua Wen , Adriane Chapman , Pei Yang , Mingnan Luo , Yingxue Xu , Dan Dai , Wendy Hall · YOU? · · 2020 · Open Access ·

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. By promoting the semantic linkage modeling of visual features, our method outperforms state-of-the-art approaches on multiple representative ZSL datasets: AwA2, CUB, and SUN.

Type

preprint

Language

en

Landing Page

http://export.arxiv.org/pdf/2006.04648

OA Status

green

Cited By

4

References

62

Related Works

20

OpenAlex ID

https://openalex.org/W3033199763

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W3033199763

Canonical identifier for this work in OpenAlex

Title

Semantic Graph-enhanced Visual Network for Zero-shot Learning

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2020

Year of publication

Publication date

2020-06-08

Full publication date if available

Authors

Yang Hu, Guihua Wen, Adriane Chapman, Pei Yang, Mingnan Luo, Yingxue Xu, Dan Dai, Wendy Hall

List of authors in order

Landing page

https://export.arxiv.org/pdf/2006.04648

Publisher landing page

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://export.arxiv.org/pdf/2006.04648

Direct OA link when available

Concepts

Computer science, Graph, Artificial intelligence, Convolutional neural network, Ambiguity, Visualization, Pattern recognition (psychology), Theoretical computer science, Natural language processing, Machine learning, Programming language

Top concepts (fields/topics) attached by OpenAlex

Cited by

4

Total citation count in OpenAlex

Citations by year (recent)

2022: 1, 2021: 3

Per-year citation counts (last 5 years)

References (count)

62

Number of works referenced by this work

Related works (count)

20

Other works algorithmically related by OpenAlex

Full payload