Joint Multi-Label Multi-Instance Learning for Image Classification
Abstract
In real world, an image is usually associated with multiple labels which are characterized by different regions in the image. Thus image classification is naturally posed as both a multi-label learning and multi-instance learning problem. Different from existing research which has considered these two problems separately, we propose an integrated multi-label multi-instance learning (MLMIL) approach based on hidden conditional random fields (HCRFs), which simultaneously captures both the connections between semantic labels and regions, and the correlations among the labels in a single formulation. We apply this MLMIL framework to image classification and report superior performance compared to key existing approaches over the MSR Cambridge (MSRC) and Corel data sets.
Cite
Text
Zha et al. "Joint Multi-Label Multi-Instance Learning for Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008. doi:10.1109/CVPR.2008.4587384Markdown
[Zha et al. "Joint Multi-Label Multi-Instance Learning for Image Classification." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2008.](https://mlanthology.org/cvpr/2008/zha2008cvpr-joint/) doi:10.1109/CVPR.2008.4587384BibTeX
@inproceedings{zha2008cvpr-joint,
title = {{Joint Multi-Label Multi-Instance Learning for Image Classification}},
author = {Zha, Zheng-Jun and Hua, Xian-Sheng and Mei, Tao and Wang, Jingdong and Qi, Guo-Jun and Wang, Zengfu},
booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
year = {2008},
doi = {10.1109/CVPR.2008.4587384},
url = {https://mlanthology.org/cvpr/2008/zha2008cvpr-joint/}
}