Skip to content

Rich feature hierarchies for accurate object detection and semantic segmentation

Authors: Girshick, R., Donahue, J., Darrell, T., & Malik, J. Year: 2014 Venue: CVPR ArXiv: https://arxiv.org/abs/1311.2524

Summary

R-CNN combines CNNs with region proposals for object detection. It dramatically improves detection accuracy and becomes the foundation for Faster R-CNN and Mask R-CNN.

Key Concepts

  • Region proposal networks
  • CNN feature extraction
  • Selective search for proposals
  • Bounding box regression
  • Two-stage detection pipeline

Impact

R-CNN revolutionized object detection and inspired a family of detectors (Fast R-CNN, Faster R-CNN, Mask R-CNN). Region-based detection remains dominant.


Citation:

@inproceedings{girshick2014rich,
  title={Rich feature hierarchies for accurate object detection and semantic segmentation},
  author={Girshick, Ross and Donahue, Jeff and Darrell, Trevor and Malik, Jitendra},
  booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2014}
}