Visual-Semantic Graph Matching Net for Zero-Shot Learning
Not on the map. Why?
Abstract (arXiv)
Zero-shot learning (ZSL) aims to leverage additional semantic information to recognize unseen classes. To transfer knowledge from seen to unseen classes, most ZSL methods often learn a shared embedding space by simply aligning visual embeddings with semantic prototypes. However, methods trained under this paradigm often struggle to learn robust embedding space because they align the two modalities in an isolated manner among classes, which ignore the crucial class relationship during the alignment process. To address the aforementioned challenges, this paper proposes a Visual-Semantic Graph Matching Net, termed as VSGMN, which leverages semantic relationships among classes to aid in visual-semantic embedding. VSGMN employs a Graph Build Network (GBN) and a Graph Matching Network (GMN) to achieve two-stage visual-semantic alignment. Specifically, GBN first utilizes an embedding-based approach to build visual and semantic graphs in the semantic space and align the embedding with its prototype for first-stage alignment. Additionally, to supplement unseen class relations in these graphs, GBN also build the unseen class nodes based on semantic relationships. In the second stage, GMN continuously integrates neighbor and cross-graph information into the constructed graph nodes, and aligns the node relationships between the two graphs under the class relationship constraint. Extensive experiments on three benchmark datasets demonstrate that VSGMN achieves superior performance in both conventional and generalized ZSL scenarios. The implementation of our VSGMN and experimental results are available at github: https://github.com/dbwfd/VSGMN
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 48 of its 78 references that are in the map. First posted on arXiv 18 Nov 2024.
Builds on
48 of 78 references.
References · 48
- 2017Attention Is All You Needcited by 60,361
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2017Graph Attention Networkscited by 8,923
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2017Prototypical Networks for Few-shot Learningcited by 3,015
- 2016Convolutional Neural Networks on Graphs with Fast Localized Spectral Filteringcited by 2,089
- 2013Spectral Networks and Locally Connected Networks on Graphscited by 1,102
- 2018Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learningcited by 1,102
- 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
- 2017Feature Generating Networks for Zero-Shot Learningcited by 257
36 more
- 2017Zero-Shot Learning -- The Good, the Bad and the Uglycited by 255
- 2013Zero-Shot Learning Through Cross-Modal Transfercited by 237
- 2018Generalized Zero- and Few-Shot Learning via Aligned Variational Autoencoderscited by 206
- 2019Graph Matching Networks for Learning the Similarity of Graph Structured Objectscited by 205
- 2019f-VAEGAN-D2: A Feature Generating Framework for Any-Shot Learningcited by 164
- 2020Attribute Prototype Network for Zero-Shot Learningcited by 160
- 2020A Review of Generalized Zero-Shot Learning Methodscited by 159
- 2018Zero-shot Recognition via Semantic Embeddings and Knowledge Graphscited by 155
- 2017Generalized Zero-Shot Learning via Synthesized Examplescited by 114
- 2021Counterfactual Zero-Shot and Open-Set Visual Recognitioncited by 95
- 2019Leveraging the Invariant Side of Generative Zero-Shot Learningcited by 83
- 2020Domain-aware Visual Bias Eliminating for Generalized Zero-Shot Learningcited by 71
- 2021FREE: Feature Refinement for Generalized Zero-Shot Learningcited by 67
- 2017Zero-Shot Visual Recognition using Semantics-Preserving Adversarial Embedding Networkscited by 66
- 2019Episode-based Prototype Generating Network for Zero-Shot Learningcited by 66
- 2019Semantic-Guided Multi-Attention Localization for Zero-Shot Learningcited by 58
- 2021HSVA: Hierarchical Semantic-Visual Adaptation for Zero-Shot Learningcited by 57
- 2017Learning Robust Visual-Semantic Embeddingscited by 56
- 2020Generalized Zero-Shot Learning Via Over-Complete Distributioncited by 56
- 2021TransZero: Attribute-guided Transformer for Zero-Shot Learningcited by 54
- 2015Transductive Multi-view Zero-Shot Learningcited by 53
- 2022MSDN: Mutually Semantic Distillation Network for Zero-Shot Learningcited by 48
- 2018Transductive Unbiased Embedding for Zero-Shot Learningcited by 44
- 2019Rethinking Zero-Shot Learning: A Conditional Visual Classification Perspectivecited by 42
- 2021TransZero++: Cross Attribute-Guided Transformer for Zero-Shot Learningcited by 28
- 2016Zero-Shot Visual Recognition via Bidirectional Latent Embeddingcited by 27
- 2018Discriminative Learning of Latent Features for Zero-Shot Recognitioncited by 24
- 2023Evolving Semantic Prototype Improves Generative Zero-Shot Learningcited by 20
- 2021Isometric Propagation Network for Generalized Zero-shot Learningcited by 18
- 2024Progressive Semantic-Guided Vision Transformer for Zero-Shot Learningcited by 17
- 2024Visual-Augmented Dynamic Semantic Prototype for Generative Zero-Shot Learningcited by 16
- 2019Alleviating Feature Confusion for Generative Zero-shot Learningcited by 10
- 2023EGANS: Evolutionary Generative Adversarial Network Search for Zero-Shot Learningcited by 6
- 2021Rethink, Revisit, Revise: A Spiral Reinforced Self-Revised Network for Zero-Shot Learningcited by 5
- 2022Diversity-boosted Generalization-Specialization Balancing for Zero-shot Learningcited by 4
- 2024Data Distribution Distilled Generative Model for Generalized Zero-Shot Recognitioncited by 4
Built on by
Citing papers per year: 2025: 2; 2026: 1.
3 papers.