Order-Free RNN with Visual Attention for Multi-Label Classification

@article{Chen2018OrderFreeRW,
  title={Order-Free RNN with Visual Attention for Multi-Label Classification},
  author={Shang-Fu Chen and Yi-Chen Chen and Chih-Kuan Yeh and Yu-Chiang Frank Wang},
  journal={CoRR},
  year={2018},
  volume={abs/1707.05495}
}
We propose a recurrent neural network (RNN) based model for image multi-label classification. Our model uniquely integrates and learning of visual attention and Long Short Term Memory (LSTM) layers, which jointly learns the labels of interest and their co-occurrences, while the associated image regions are visually attended. Different from existing approaches utilize either model in their network architectures, training of our model does not require pre-defined label orders. Moreover, a robust… CONTINUE READING

5 Figures & Tables

Topics

Statistics

0102020172018
Citations per Year

Citation Velocity: 7

Averaging 7 citations per year over the last 2 years.

Learn more about how we calculate this metric in our FAQ.