Channel-Wise and Feature-Points Reweights Densenet for Image Classification

Ke Zhang, Yurong Guo, Xinsheng Wang, Jinsha Yuan, Zhanyu Ma, Zhenbing Zhao

Abstract

Recent network research has demonstrated that the performance of convolutional neural networks can be improved by introducing a learning block that capture spatial correlations and channel-wise correlations . In this work, we propose a novel Channel-wise and Feature-points Reweights DenseNet (CAPR-DenseNet) architecture. The CAPR-DenseNet improves the representation power of the DenseNet by adaptively recalibrating the channel-wise feature responses and explicitly modeling the interdependencies between feature-points. First, in order to perform dynamic channel-wise feature recalibration, we construct the Channel-wise Feature Reweight DenseNet (CFR-DenseNet) by introducing the Squeeze-and-Excitation Module (SEM) to DenseNet. Then, we present a novel CAPR-DenseNet by adding a Feature-points Reweight Module (FPRM) to the CFR-DenseNet. Through massive experiments, we demonstrate that by recalibrating the channel-wise feature and the feature-points responses. Our CAPR-DenseNet performs better than DenseNet across challenging datasets CIFAR-10 and CIFAR-100.
BibTeX
@inproceedings{zhang2019channel,
  author = {Ke Zhang and Yurong Guo and Xinsheng Wang and Jinsha Yuan and Zhanyu Ma and Zhenbing Zhao},
  title = {{Channel-Wise and Feature-Points Reweights Densenet for Image Classification}},
  booktitle = {ICIP},
  year = {2019},
  doi = {10.1109/icip.2019.8802982},
}

Loading related content...

Figure