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.
Related Papers¶
- Faster R-CNN: Towards Real-Time Object Detection
- Mask R-CNN: Instance Segmentation
- YOLO: Real-Time Object Detection
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}
}