Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks

@article{Ren2015FasterRT,
  title={Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks},
  author={Shaoqing Ren and Kaiming He and Ross B. Girshick and Jian Sun},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2015},
  volume={39},
  pages={1137-1149}
}

• Shaoqing Ren, Kaiming He, +1 author Jian Sun
• Published in
  IEEE Transactions on Pattern Analysis and Machine…
  2015
• DOI:10.1109/TPAMI.2016.2577031

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet <xref ref-type="bibr" rid="ref1">[1]</xref> and Fast R-CNN <xref ref-type="bibr" rid="ref2">[2]</xref> have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a <italic>Region Proposal Network</italic> (RPN) that shares full-image convolutional features with the detection network… CONTINUE READING

View on IEEE

Save to Library

Create Alert

Cite