Region Based Convolutional Neural Networks: Difference between revisions

Revision as of 23:47, 12 March 2020

Revision as of 22:46, 29 March 2020

Line 8:

* April 2015: '''Fast R-CNN'''. While the original R-CNN ran the neural network on each of as many as 2000 regions of interest (ROI), Fast R-CNN runs the neural network once on the whole image. At the end of the network is a novel method called ROI pooling, which slices out each ROI from the network's output tensor, reshapes it, and classifies it.<ref name=":0">{{Cite news|last=Bhatia|first=Richa|url=https://analyticsindiamag.com/what-is-region-of-interest-pooling/|title=What is region of interest pooling?|date=September 10, 2018|work=Analytics India|access-date=March 12, 2020|url-status=live}}</ref> As in the original R-CNN, the Fast R-CNN uses Selective Search to generate its region proposals.

* June 2015: '''Faster R-CNN'''. While Fast R-CNN used Selective Search to generate ROIs, Faster R-CNN integrates the ROI generation into the neural network itself.<ref name=":0" />

* March 2017: '''Mask R-CNN'''. (workWhile inprevious progress;versions needof toR-CNN summarizefocused on object detection, Mask R-CNN adds instance segmentation. Mask R-CNN also replaced ROI pooling with a new method called ROIAlign), which can represent fractions of a pixel.<ref>{{Cite news|last=Farooq|first=Umer|url=https://medium.com/@umerfarooq_26378/from-r-cnn-to-mask-r-cnn-d6367b196cfd|title=From R-CNN to Mask R-CNN|date=February 15, 2018|work=Medium|access-date=March 12, 2020|url-status=live}}</ref><ref>{{Cite news|last=Weng|first=Lilian|url=https://lilianweng.github.io/lil-log/2017/12/31/object-recognition-for-dummies-part-3.html|title=Object Detection for Dummies Part 3: R-CNN Family|date=December 31, 2017|work=Lil'Log|access-date=March 12, 2020|url-status=live}}</ref>

* (June 2019): '''Mesh R-CNN'''. (adds the ability to summarize)generate a 3D mesh from a 2D image.<ref>{{Cite news|last=Wiggers|first=Kyle|url=https://venturebeat.com/2019/10/29/facebook-highlights-ai-that-converts-2d-objects-into-3d-shapes/|title=Facebook highlights AI that converts 2D objects into 3D shapes|date=October 29, 2019|work=VentureBeat|access-date=March 12, 2020|url-status=live}}</ref>

<br />

== Applications ==

Region Based Convolutional Neural Networks have been used for tracking objects from a drone-mounted camera,<ref>{{Cite news|last=Nene|first=Vidi|url=https://dronebelow.com/2019/08/02/deep-learning-based-real-time-multiple-object-detection-and-tracking-via-drone/|title=Deep Learning-Based Real-Time Multiple-Object Detection and Tracking via Drone|date=Aug 2, 2019|work=Drone Below|access-date=Mar 28, 2020|url-status=live}}</ref> locating text in an image,<ref>{{Cite news|last=Ray|first=Tiernan|url=https://www.zdnet.com/article/facebook-pumps-up-character-recognition-to-mine-memes/|title=Facebook pumps up character recognition to mine memes|date=Sep 11, 2018|work=ZDnet|access-date=Mar 28, 2020|url-status=live}}</ref> and enabling object detection in [[Google Lens]].<ref>{{Cite news|last=Sagar|first=Ram|url=https://analyticsindiamag.com/these-machine-learning-techniques-make-google-lens-a-success/|title=These machine learning methods make google lens a success|date=Sep 9, 2019|work=Analytics India|access-date=Mar 28, 2020|url-status=live}}</ref> Mask R-CNN serves as one of seven tasks in the MLPerf Training Benchmark, which is a competition to speed up the training of neural networks.

(starting with a bibliography; will clean up)

* https://dronebelow.com/2019/08/02/deep-learning-based-real-time-multiple-object-detection-and-tracking-via-drone/

* https://venturebeat.com/2019/04/24/google-open-sources-ai-image-segmentation-models-optimized-for-cloud-tpus/

* https://www.zdnetsyncedreview.com/article2019/12/26/facebook-pumps-up-character-recognitionpointrend-torendering-mineimage-memessegmentation/

* https://syncedreview.com/2019/03/12/26/facebooknew-pointrendsota-renderingon-imageinstance-segmentation-mask-scoring-r-cnn-tops-mask-r-cnn-on-coco/

* https://analyticsindiamag.com/these-machine-learning-techniques-make-google-lens-a-success/

* https://syncedreview.com/2019/03/12/new-sota-on-instance-segmentation-mask-scoring-r-cnn-tops-mask-r-cnn-on-coco/

* fast training - https://siliconangle.com/2019/07/10/nvidia-sets-new-records-mlperf-ai-benchmark-tests/

*The MLPerf benchmark tests how fast a computing platform can train Mask R-CNN.

*