arrow
返回

Graph embedding based multi-label Zero-shot Learning

delete2023-10-01
delete6
delete
OA
AI
H
Haigang Zhang
孟
孟祥龙 (Xianglong Meng)
W
Weipeng Cao *
Y
Ye Liu
Z
Zhong, Ming
J
Jinfeng Yang
DOI:10.1016/j.neunet.2023.08.023delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
Multi-label Zero-shot Learning (ZSL) is more reasonable and realistic than standard single-label ZSL because several objects can co-exist in a natural image in real scenarios. Intra-class feature entanglement is a significant factor influencing the alignment of visual and semantic features, resulting in the model's inability to recognize unseen samples comprehensively and completely. We observe that existing multi-label ZSL methods place a greater emphasis on attention-based refinement and decoupling of visual features, while ignoring the relationship between label semantics. Relying on label correlations to solve multi-label ZSL tasks has not been deeply studied. In this paper, we make full use of the co-occurrence relationship between category labels and build a directed weighted semantic graph based on statistics and prior knowledge, in which node features represent category semantics and weighted edges represent conditional probabilities of label co-occurrence. To guide the targeted extraction of visual features, node features and edge set weights are simultaneously updated and refined, and embedded into the visual feature extraction network from a global and local perspective. The proposed method's effectiveness was demonstrated by simulation results on two challenging multi-label ZSL benchmarks: NUS-WIDE and Open Images. In comparison to stateof-the-art models, our model achieves an absolute gain of 2.4% mAP on NUS-WIDE and 2.1% mAP on Open Images respectively.(c) 2023 Elsevier Ltd. All rights reserved.
Keyword:
Zero-shot Learning
Knowledge graph
Multi-label classification
Feature embedding
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Neural Networks 封面图
Neural Networks
IF:
6.3
论文数:
8.4K
被引数:
3.9W

机构

南方医科大学 封面图
南方医科大学
学者数:
4.6W
论文数: 2.5W
被引数: 3.4W
深圳职业技术大学 封面图
深圳职业技术大学
学者数:
347
论文数: 172
被引数: 1.9K
引用论文

引用论文

Compact network embedding for fast node classification用于快速节点分类的紧凑网络嵌入
err2023-04-01
err4
PREAI
errShen, Xiaobo; Ong, Yew-Soon; Mao, Zheng; Pan, Shirui; Liu, Weiwei; Zheng, Yuhui
err分享
err收藏
Automated multi-label text categorization with VG-RAM weightless neural networks使用vg-ram失重神经网络进行自动多标签文本分类
err2009-06-01
err36
PREAI
errDe Souza, Alberto F.; Pedroni, Felipe; Oliveira, Elias; Ciarelli, Patrick M.; Henrique, Wallace Favoreto; Veronese, Lucas; Badue, Claudine
err分享
err收藏
Investigating the Bilateral Connections in Generative Zero-Shot Learning
err2022-08-01
err37
PREAI
errLi, Jingjing; Jing, Mengmeng; Lu, Ke; Zhu, Lei; Shen, Heng Tao
err分享
err收藏
Generative Adversarial Networks An overview生成对抗网络综述
err2018-01-01
err2.4K
errOAAI
errCreswell, Antonia; White, Tom; Dumoulin, Vincent; Arulkumaran, Kai; Sengupta, Biswa; Bharath, Anil A.
err分享
err收藏
The Open Images Dataset V4 Unified Image Classification, Object Detection, and Visual Relationship Detection at Scale
err2020-03-13
err1.1K
PREAI
errKuznetsova, Alina; Rom, Hassan; Alldrin, Neil; Uijlings, Jasper; Krasin, Ivan; Pont-Tuset, Jordi; Kamali, Shahab; Popov, Stefan; Malloci, Matteo; Kolesnikov, Alexander; Duerig, Tom; Ferrari, Vittorio
err分享
err收藏
err分享
err收藏
Research progress of zero-shot learning
err2020-11-16
err39
PREAI
errSun, Xiaohong; Gu, Jinan; Sun, Hongying
err分享
err收藏
学者 查看更多内容