Object Detection for Dummies Part 3: R-CNN Family
Lilian Weng
This article reviews the R-CNN family of object detection models, building on previous parts covering image processing fundamentals and classic CNN architectures. The post includes updates from December 2018 clarifying that YOLO will be covered separately in Part 4 and adding sections on bounding box regression and R-CNN techniques. The series progresses systematically from basic concepts through CNN designs to region-based detection approaches.
Why it matters
[Updated on 2018-12-20: Remove YOLO here. Part 4 will cover multiple fast object detection algorithms, including YOLO.] [Updated on 2018-12-27: Add bbox regression and tricks sections for R-CNN.] In the series of “Object Detection for Dummies”, we started with basic concepts in image processing, such as gradient vectors and HOG, in Part 1. Then we introduced classic convolutional neural network architecture designs for classification and pioneer models for object recognition, Overfeat and DPM, in Part 2. In the third post of this series, we are about to review a set of models in the R-CNN (“Region-based CNN”) family.
