AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification

54Citations
Citations of this article
51Readers
Mendeley users who have this article in their library.
Get full text

Abstract

Multi-label image classification is an important and challenging task in computer vision and multimedia fields. Most of the recent works only capture the pair-wise dependencies among multiple labels through statistical co-occurrence information, which cannot model the high-order semantic relations automatically. In this paper, we propose a high-order semantic learning model based on adaptive hypergraph neural networks (AdaHGNN) to boost multi-label classification performance. Firstly, an adaptive hypergraph is constructed by using label embeddings automatically. Secondly, image features are decoupled into feature vectors corresponding to each label, and hypergraph neural networks (HGNN) are employed to correlate these vectors and explore the high-order semantic interactions. In addition, multi-scale learning is used to reduce sensitivity to object size inconsistencies. Experiments are conducted on four benchmarks: MS-COCO, NUS-WIDE, Visual Genome, and Pascal VOC 2007, which cover large, medium, and small-scale categories. State-of-the-art performances are achieved on three of them. Results and analysis demonstrate that the proposed method has the ability to capture high-order semantic dependencies.

References Powered by Scopus

Deep residual learning for image recognition

178837Citations
N/AReaders
Get full text

ImageNet: A Large-Scale Hierarchical Image Database

52564Citations
N/AReaders
Get full text

Microsoft COCO: Common objects in context

29716Citations
N/AReaders
Get full text

Cited by Powered by Scopus

A Survey on Hypergraph Representation Learning

68Citations
N/AReaders
Get full text

A multi-scale semantic attention representation for multi-label image recognition with graph networks

35Citations
N/AReaders
Get full text

Semantic-Aware Representation Blending for Multi-Label Image Recognition with Partial Labels

30Citations
N/AReaders
Get full text

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Wu, X., Chen, Q., Li, W., Xiao, Y., & Hu, B. (2020). AdaHGNN: Adaptive Hypergraph Neural Networks for Multi-Label Image Classification. In MM 2020 - Proceedings of the 28th ACM International Conference on Multimedia (pp. 284–293). Association for Computing Machinery, Inc. https://doi.org/10.1145/3394171.3414046

Readers over time

‘20‘21‘22‘23‘24‘250481216

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 13

72%

Researcher 3

17%

Lecturer / Post doc 2

11%

Readers' Discipline

Tooltip

Computer Science 15

75%

Engineering 3

15%

Medicine and Dentistry 1

5%

Psychology 1

5%

Save time finding and organizing research with Mendeley

Sign up for free
0