Spatial-context-aware deep neural network for multi-class image classification

2021/11/24 by Jialu Zhang, Zhang, Jialu, Qian Zhang +7 · 1 citation
Biochemistry, Genetics and Molecular Biology · Computer Science · #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Image Retrieval and Classification Techniques #Machine Learning in Bioinformatics #Text and Document Classification Technologies

paper · pdf · doi:10.48550/arxiv.2111.12296

openalex publication_date 2021/11/24 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

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.

Cited by

• Face recognition on point cloud with cgan-top for denoising

Related

• Learning Spatial Regularization with Image-level Supervisions for Multi-label Image Classification
• Multi-label Classification using Deep Multi-order Context-aware Kernel Networks
• Semantic Embedded Deep Neural Network: A Generic Approach to Boost Multi-Label Image Classification Performance
• A Baseline for Multi-Label Image Classification Using An Ensemble of Deep Convolutional Neural Networks
• Multi-label Classification with Panoptic Context Aggregation Networks