Active learning in multi-label image classification with graph convolutional network embedding

Xiurui Xie, Maojun Tian, Guangchun Luo, Guisong Liu, Yizhe Wu, Ke Qin

Abstract: Highlights•We propose an active learning framework with a GCN embedding and loss prediction module.•We propose a dynamic to adjust the AL proportion for more effective sample selection.•The extensive multi-label experiment displays the efficacy of the proposed approach.