返回
Graph embedding based multi-label Zero-shot Learning
DOI:10.1016/j.neunet.2023.08.023.png)
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
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
IF:
6.3
论文数:
8.4K
被引数:
3.9W
机构
引用论文
Transcatheter occlusion of the persistently patent ductus arteriosus. Forty-month follow-up and prevalence of residual shunting.
Circulation
IF0
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
NEUROCOMPUTING
IF6.5
Visual-guided attentive attributes embedding for zero-shot learning视觉引导的注意力属性嵌入,用于零射击学习
NEURAL NETWORKS
IF6.3

