DeepBE: Learning Deep Binary Encoding for Multi-label Classification

@article{Li2016DeepBELD,
  title={DeepBE: Learning Deep Binary Encoding for Multi-label Classification},
  author={Chenghua Li and Qi Kang and Guojing Ge and Qiang Song and Hanqing Lu and Jian Cheng},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)},
  year={2016},
  pages={744-751}
}
The track 2 and track 3 of ChaLearn 2016 can be considered as Multi-Label Classification problems. We present a framework of learning deep binary encoding (DeepBE) to deal with multi-label problems by transforming multi-labels to single labels. The transformation of DeepBE is in a hidden pattern, which can be well addressed by deep convolutions neural networks (CNNs). Furthermore, we adopt an ensemble strategy to enhance the learning robustness. This strategy is inspired by its effectiveness in… CONTINUE READING