.png){kind=icon}
返回
Large-scale multi-label classification using unknown streaming images
.png){kind=icon}
PRE
AI
DOI：10.1016/j.patcog.2019.107100.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this paper, we investigate the large-scale multi-label image classification problem when images with unknown novel classes come in stream during the training stage. It coincides with the practical requirement that usually novel classes are detected and used to update an existing image recognition system. Most existing multi-label image classification methods cannot be directly applied in this scenario, where the training and testing stages must have the same label set. In this paper, we proposed to learn a multi-label classifier and a novel-class detector alternately to solve this problem. The multi-label classifier is learned using a convolutional neural network (CNN) from the images in the known classes. We proposed a recurrent novel-class detector which is learned in the supervised manner to detect the novel class by encoding image features with the multi-label information. In the experiment, our method is evaluated on several large-scale multi-label benchmarks including MS COCO. The results show the proposed method is comparable to most existing multi-label image classification methods, which validate its efficacy when encountering streaming images with unknown classes. (C) 2019 Elsevier Ltd. All rights reserved.
Keyword:
Multi-label image classification
Recurrent novel-class detector
Streaming images
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:
7.6
论文数:
1.3W
被引数:
4.5W
机构
引用论文
ML-KNN: A lazy learning approach to multi-label leamingMl-knn: 一种多标签学习的懒惰学习方法.png)
PATTERN RECOGNITION
OAAI
PATTERN RECOGNITIONIF7.6
OAAI分享收藏Unsupervised object discovery and co-localization by deep descriptor transformationPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
分享收藏Classification Under Streaming Emerging New Classes: A Solution Using Completely-Random Trees流新兴类别下的分类: 使用完全随机树的解决方案OAAI
OAAI分享收藏
查看更多内容