A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation

doi:10.1007/s11633-023-1439-3

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation
	Feng Sun; Ming-Kun Xie; Sheng-Jun Huang
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:4 页码:801-814
摘要	In this paper, we study the partial multi-label (PML) image classification problem, where each image is annotated with a candidate label set consisting of multiple relevant labels and other noisy labels. Existing PML methods typically design a disambiguation strategy to filter out noisy labels by utilizing prior knowledge with extra assumptions, which unfortunately is unavailable in many real tasks. Furthermore, because the objective function for disambiguation is usually elaborately designed on the whole training set, it can hardly be optimized in a deep model with stochastic gradient descent (SGD) on mini-batches. In this paper, for the first time, we propose a deep model for PML to enhance the representation and discrimination ability. On the one hand, we propose a novel curriculum-based disambiguation strategy to progressively identify ground-truth labels by incorporating the varied difficulties of different classes. On the other hand, consistency regularization is introduced for model training to balance fitting identified easy labels and exploiting potential relevant labels. Extensive experimental results on the commonly used benchmark datasets show that the proposed method significantly outperforms the SOTA methods.
关键词	Partial multi-label image classification curriculum-based disambiguation consistency regularization label difficulty candidate label set.
DOI	10.1007/s11633-023-1439-3
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58573
专题	学术期刊_Machine Intelligence Research
作者单位	MIIT Key Laboratory of Pattern Analysis and Machine Intelligence, College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China
推荐引用方式 GB/T 7714	Feng Sun,Ming-Kun Xie,Sheng-Jun Huang. A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation[J]. Machine Intelligence Research,2024,21(4):801-814.
APA	Feng Sun,Ming-Kun Xie,&Sheng-Jun Huang.(2024).A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation.Machine Intelligence Research,21(4),801-814.
MLA	Feng Sun,et al."A Deep Model for Partial Multi-label Image Classification with Curriculum-based Disambiguation".Machine Intelligence Research 21.4(2024):801-814.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2022-11-348.pdf（1337KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载