SPATIAL-CONTEXT-AWARE DEEP NEURAL NETWORK FOR MULTI-CLASS IMAGE CLASSIFICATION

Zhang，Jialu1,2; Zhang，Qian1; Ren，Jianfeng1; Zhao，Yitian2; Liu，Jiang1,2,3

10.1109/ICASSP43922.2022.9746921

2022

47th IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

1520-6149

978-1-6654-0541-6

ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

2022-May

1960-1964

23-27 May 2022

Singapore, Singapore

345 E 47TH ST, NEW YORK, NY 10017 USA

IEEE

Multi-label image classification is a fundamental but challenging task in computer vision. Over the past few decades, solutions exploring relationships between semantic labels have made great progress. However, the underlying spatial-contextual information of labels is under-exploited. To tackle this problem, a spatial-context-aware deep neural network is proposed to predict labels taking into account both semantic and spatial information. This proposed framework is evaluated on Microsoft COCO and PASCAL VOC, two widely used benchmark datasets for image multi-labelling. The results show that the proposed approach is superior to the state-of-the-art solutions on dealing with the multi-label image classification problem.

deep learning image classification Multi-label spatial context

Corresponding

English

EI ; CPCI-S

Ningbo Municipal Bureau of Science and Technology[2019B10026];National Natural Science Foundation of China[72071116];

Acoustics ; Computer Science ; Engineering

Acoustics ; Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic

WOS:000864187902047

20222312199011

2-s2.0-85131259273

Scopus

1.School of Computer Science,University of Nottingham,Ningbo,China
2.Cixi Institute of Biomedical Engineering,Chinese Academy of Sciences,China
3.Department of Computer Science and Engineering,Southern University of Science and Technology,China

Zhang，Jialu,Zhang，Qian,Ren，Jianfeng,et al. SPATIAL-CONTEXT-AWARE DEEP NEURAL NETWORK FOR MULTI-CLASS IMAGE CLASSIFICATION[C]. 345 E 47TH ST, NEW YORK, NY 10017 USA:IEEE,2022:1960-1964.