Skip to content

Rich feature hierarchies for accurate object detection and semantic segmentation (R-CNN)

Authors: Ross Girshick, Jeff Donahue, Trevor Darrell, Jitendra Malik Year: 2014 Citations: 40,000+

Summary

R-CNN combines region proposals with CNNs for object detection. Selective search generates regions, pre-trained CNN extracts features, SVM classifies. Foundation of modern object detection.

Key Concepts

  • Region Proposals: Selective search candidates
  • CNN Feature Extraction: Pre-trained ImageNet features
  • Classification: SVM for object recognition
  • Bounding Box Regression: Refines region coordinates
  • Transfer Learning: Pre-trained CNN features applied
  • Two-Stage Detection: Proposes then classifies

Impact

  • 40,000+ citations
  • Triggered object detection revolution
  • Showed transfer learning effectiveness
  • Foundation for Faster R-CNN, Mask R-CNN
  • Influenced two-stage detector design
  • Connected region proposals with deep learning
  • Fast R-CNN (Girshick, 2015)
  • Faster R-CNN (Ren et al., 2015)
  • YOLO (Redmon et al., 2016)