.png){kind=icon}
返回
Transductive semantic knowledge graph propagation for zero-shot learning
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jfranklin.2023.07.009.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
The domain shift is a very common phenomenon in Zero-shot Learning (ZSL), because the data distribution between the source and target domain might not match well in real scenarios. This paper focuses on dealing with the domain drift problem in ZSL based on the semantic knowledge graph propagation. Our method consists of visual feature extraction (VFE) module, semantic feature extraction module (SFE) and feature mapping module (FM). In VFE module, the high-level visual features are extracted under Convolutional Neural Network (CNN) framework, where unseen samples participate in model training and stay away from seen ones under the premise of distinguishability. SFE module relies on the Graph Convolutional Network (GCN) framework and focuses on the transmission of semantic embeddings. A modified message aggregation and transformation strategy is proposed to effectively relieve the information smoothing phenomenon caused by the increase of GCN layers. In the recognition stage, AutoEncoder framework achieves a two-way visual and semantic interaction to further minimize the domain drift phenomenon. Simulation results on ImageNet dataset have demonstrated the performance of the proposed method.(c) 2023 The Franklin Institute. Published by Elsevier Inc. All rights reserved.
期刊
J
IF:
3.7
论文数:
6.4K
被引数:
1.5W
机构
查看更多机构
引用论文
RECOGNITION-BY-COMPONENTS - A THEORY OF HUMAN IMAGE UNDERSTANDING按组件识别-人类图像理解的理论.png)
PSYCHOLOGICAL REVIEW
OAAI
PSYCHOLOGICAL REVIEWIF5.8
OAAI分享收藏Boosting Zero-Shot Learning via Contrastive Optimization of Attribute Representations通过属性表示的对比优化来促进零射学习
OAAI
OAAI分享收藏 没有更多内容