Spatial-context-aware deep neural network for multi-class image classification
This work addresses the challenge of under-exploited spatial-contextual information in multi-label image classification for computer vision applications, representing an incremental improvement.
The paper tackled the problem of multi-label image classification by proposing a spatial-context-aware deep neural network that exploits spatial-contextual information of labels, achieving superior results compared to state-of-the-art solutions on Microsoft COCO and PASCAL VOC datasets.
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.