Region-based Convolutional Neural Networks (R-CNN) are a family of machine learning models for computer vision, and specifically object detection and localization.[1] The original goal of R-CNN was to take an input image and produce a set of bounding boxes as output, where each bounding box contains an object and also the category (e.g. car or pedestrian) of the object. In general, R-CNN architectures perform selective search[2] over feature maps outputted by a CNN.
![](http://upload.wikimedia.org/wikipedia/commons/thumb/c/cd/R-cnn.svg/272px-R-cnn.svg.png)
R-CNN has been extended to perform other computer vision tasks, such as: tracking objects from a drone-mounted camera,[3] locating text in an image,[4] and enabling object detection in Google Lens.[5]
Mask R-CNN is also one of seven tasks in the MLPerf Training Benchmark, which is a competition to speed up the training of neural networks.[6]
History
editThe following covers some of the versions of R-CNN that have been developed.
Architecture
editFor review articles see.[1][12]
Selective search
editGiven an image (or an image-like feature map), selective search (also called Hierarchical Grouping) first segments teh image by the algorithm in Felzenszwalb and Huttenlocher (2004),[13] then performs the following:[2]
Input: (colour) image
Output: Set of object location hypotheses L
Segment image into initial regions R = {r₁, ..., rₙ} using Felzenszwalb and Huttenlocher (2004)
Initialise similarity set S = ∅
foreach Neighbouring region pair (rᵢ, rⱼ) do
Calculate similarity s(rᵢ, rⱼ)
S = S ∪ s(rᵢ, rⱼ)
while S ≠ ∅ do
Get highest similarity s(rᵢ, rⱼ) = max(S)
Merge corresponding regions rₜ = rᵢ ∪ rⱼ
Remove similarities regarding rᵢ: S = S \ s(rᵢ, r∗)
Remove similarities regarding rⱼ: S = S \ s(r∗, rⱼ)
Calculate similarity set Sₜ between rₜ and its neighbours
S = S ∪ Sₜ
R = R ∪ rₜ
Extract object location boxes L from all regions in R
R-CNN
editGiven an input image, R-CNN begins by applying a mechanism called selective search[2] to extract regions of interest (ROI), where each ROI is a rectangle that may represent the boundary of an object in image. Depending on the scenario, there may be as many as two thousand ROIs. After that, each ROI is fed through a neural network to produce output features. For each ROI's output features, a collection of support-vector machine classifiers is used to determine what type of object (if any) is contained within the ROI.[7]
Fast R-CNN
editWhile the original R-CNN independently computed the neural network features on each of as many as two thousand regions of interest, Fast R-CNN runs the neural network once on the whole image.[8]
At the end of the network is a ROIPooling module, which slices out each ROI from the network's output tensor, reshapes it, and classifies it. As in the original R-CNN, the Fast R-CNN uses selective search to generate its region proposals.
Faster R-CNN
editWhile Fast R-CNN used selective search to generate ROIs, Faster R-CNN integrates the ROI generation into the neural network itself.[9]
Mask R-CNN
editWhile previous versions of R-CNN focused on object detection, Mask R-CNN adds instance segmentation. Mask R-CNN also replaced ROIPooling with a new method called ROIAlign, which can represent fractions of a pixel.[10]
References
edit- ^ a b Zhang, Aston; Lipton, Zachary; Li, Mu; Smola, Alexander J. (2024). "14.8. Region-based CNNs (R-CNNs)". Dive into deep learning. Cambridge New York Port Melbourne New Delhi Singapore: Cambridge University Press. ISBN 978-1-009-38943-3.
- ^ a b c Uijlings, J. R. R.; van de Sande, K. E. A.; Gevers, T.; Smeulders, A. W. M. (2013-09-01). "Selective Search for Object Recognition". International Journal of Computer Vision. 104 (2): 154–171. doi:10.1007/s11263-013-0620-5. ISSN 1573-1405.
- ^ Nene, Vidi (Aug 2, 2019). "Deep Learning-Based Real-Time Multiple-Object Detection and Tracking via Drone". Drone Below. Retrieved Mar 28, 2020.
- ^ Ray, Tiernan (Sep 11, 2018). "Facebook pumps up character recognition to mine memes". ZDNET. Retrieved Mar 28, 2020.
- ^ Sagar, Ram (Sep 9, 2019). "These machine learning methods make google lens a success". Analytics India. Retrieved Mar 28, 2020.
- ^ Mattson, Peter; et al. (2019). "MLPerf Training Benchmark". arXiv:1910.01500v3 [math.LG].
- ^ a b Girshick, Ross; Donahue, Jeff; Darrell, Trevor; Malik, Jitendra (2016-01-01). "Region-Based Convolutional Networks for Accurate Object Detection and Segmentation". IEEE Transactions on Pattern Analysis and Machine Intelligence. 38 (1): 142–158. doi:10.1109/TPAMI.2015.2437384. ISSN 0162-8828.
- ^ a b Girshick, Ross (7–13 December 2015). "Fast R-CNN". 2015 IEEE International Conference on Computer Vision (ICCV). IEEE: 1440–1448. doi:10.1109/ICCV.2015.169. ISBN 978-1-4673-8391-2.
- ^ a b Ren, Shaoqing; He, Kaiming; Girshick, Ross; Sun, Jian (2017-06-01). "Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks". IEEE Transactions on Pattern Analysis and Machine Intelligence. 39 (6): 1137–1149. arXiv:1506.01497. doi:10.1109/TPAMI.2016.2577031. ISSN 0162-8828.
- ^ a b He, Kaiming; Gkioxari, Georgia; Dollar, Piotr; Girshick, Ross (October 2017). "Mask R-CNN". IEEE: 2980–2988. doi:10.1109/ICCV.2017.322. ISBN 978-1-5386-1032-9.
{{cite journal}}
: Cite journal requires|journal=
(help) - ^ Gkioxari, Georgia; Malik, Jitendra; Johnson, Justin (2019). "Mesh R-CNN": 9785–9795.
{{cite journal}}
: Cite journal requires|journal=
(help) - ^ Weng, Lilian (December 31, 2017). "Object Detection for Dummies Part 3: R-CNN Family". Lil'Log. Retrieved March 12, 2020.
- ^ Felzenszwalb, Pedro F.; Huttenlocher, Daniel P. (2004-09-01). "Efficient Graph-Based Image Segmentation". International Journal of Computer Vision. 59 (2): 167–181. doi:10.1023/B:VISI.0000022288.19776.77. ISSN 1573-1405.
Further reading
edit- Parthasarathy, Dhruv (2017-04-27). "A Brief History of CNNs in Image Segmentation: From R-CNN to Mask R-CNN". Medium. Retrieved 2024-09-11.