deep learning and computer vision · 2020-05-01 · deep learning and computer vision ryan fox...
TRANSCRIPT
![Page 1: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/1.jpg)
Deep Learning and Computer Vision
Ryan FoxMilwaukee Machine Learning12/5/17
![Page 2: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/2.jpg)
Ryan FoxEmail: [email protected]: https://foxrow.comTwitter: @ryan_fox
![Page 3: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/3.jpg)
Deep Learning and Computer Vision
What is computer vision?How can CNNs help?How can I use it?
![Page 4: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/4.jpg)
Deep Learning and Computer Vision
What is computer vision?How can CNNs help?How can I use it?
![Page 5: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/5.jpg)
What is computer vision?
- Imagery or video- Gain information at a high level of
abstraction- Often emulate human vision at computer
speed and scale
![Page 6: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/6.jpg)
Computer vision applications
Drones - 3D modeling
![Page 7: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/7.jpg)
Computer vision applications
Image classificationgrass, outdoor, people, large, field, park, group, sitting, table, man, standing, grassy, cake, crowd, display, ball, riding, horse, air, umbrella
![Page 8: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/8.jpg)
Computer vision applications
Object recognition
![Page 9: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/9.jpg)
Computer vision applications
OCR (AKA reading)
![Page 10: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/10.jpg)
Deep Learning and Computer Vision
What is computer vision?How can CNNs help?How can I use it?
![Page 11: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/11.jpg)
How can CNNs help?
What’s a convolution?
![Page 12: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/12.jpg)
Convolution
https://commons.wikimedia.org/wiki/File:Comparison_convolution_correlation.svg
![Page 13: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/13.jpg)
Convolution
1 2 1
2 4 2
1 2 1
0 2 1 5
4 8 6 8
1 2 2 9
2 1 1 7
(0*1 + 2*2 + 1*1 + 4*2 + 8*4 + 6*2 + 1*1 + 2*2 + 2*1)/16 = 4
X / 16 =4
![Page 14: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/14.jpg)
Convolution
1 2 1
2 4 2
1 2 1
0 2 1 5
4 8 6 8
1 2 2 9
2 1 1 7
(2*1 + 1*2 + 5*1 + 8*2 + 6*4 + 8*2 + 2*1 + 2*2 + 9*1)/16 = 5
X / 16 =4 5
![Page 15: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/15.jpg)
Convolution
http://cs231n.github.io/assets/cnnvis/filt1.jpeg
![Page 16: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/16.jpg)
Convolution
https://papers.nips.cc/paper/4824-imagenet-classification-with-deep-convolutional-neural-networks.pdf (17k+ citations!)
![Page 17: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/17.jpg)
How can CNNs help?
2011 ImageNet - 26% top-5 error2012 ImageNet - 15% top-5 error
http://image-net.org/challenges/talks/2016/ILSVRC2016_10_09_clsloc.pdf
![Page 18: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/18.jpg)
How can CNNs help?
CNNs are good at:- Single data points- Recognizing a broad
number of classes- Known knowns
CNNs are bad at:- Combining multiple
images- Time series data- Small training
corpora/novel items
![Page 19: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/19.jpg)
How can CNNs help?
Image classificationgrass, outdoor, people, large, field, park, group, sitting, table, man, standing, grassy, cake, crowd, display, ball, riding, horse, air, umbrella
![Page 20: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/20.jpg)
How can CNNs help?
Object recognition
![Page 21: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/21.jpg)
How can CNNs help?
Face/person detection
Finding Tiny Faces, Hu, Ramanan, https://arxiv.org/abs/1612.04402v1
![Page 22: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/22.jpg)
How can CNNs help?
Segmentation
http://cs231n.stanford.edu/slides/2016/winter1516_lecture8.pdf
![Page 23: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/23.jpg)
How can CNNs help?
NSFW classification
![Page 24: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/24.jpg)
How can CNNs help?
OCR
Artificial neural networks based vehicle license plate recognition, Kocer, Cevik, https://www.sciencedirect.com/science/article/pii/S1877050910005442
![Page 25: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/25.jpg)
How can CNNs help?
Superresolution
Image Super-Resolution Using Deep Convolutional Networks, Dong et al., https://arxiv.org/pdf/1501.00092.pdf
![Page 26: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/26.jpg)
How can CNNs help?
Generative Adversarial Networks
Intriguing properties of neural networks, Szegedy et al., https://arxiv.org/pdf/1312.6199v4.pdf
![Page 27: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/27.jpg)
Notable CNN architectures
Classification:- VGG16/VGG19- ResNet
![Page 28: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/28.jpg)
Notable CNN architectures
Inception
https://research.googleblog.com/2015/06/inceptionism-going-deeper-into-neural.html
![Page 29: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/29.jpg)
Notable CNN architectures
Localization:- R-CNN/Fast R-CNN/Faster R-CNN- YOLO/YOLOv2/YOLO9000
![Page 30: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/30.jpg)
Notable CNN architectures
- Xception- MobileNet/SqueezeNet
![Page 31: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/31.jpg)
Deep Learning and Computer Vision
What is computer vision?How can CNNs help?How can I use it?
![Page 32: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/32.jpg)
How can I use it?
Keras - https://keras.io
https://blog.keras.io/building-powerful-image-classification-models-using-very-little-data.html
![Page 34: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/34.jpg)
How can I use it?
DIL - https://github.com/foxrow/dilload DJI_001.jpghighlight person car
![Page 35: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/35.jpg)
How can I use it?
AWS, GCP, Azure vision APIs
![Page 36: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/36.jpg)
How can I use it?
Resources:https://keras.io/https://opencv.org/http://www.image-net.org/https://github.com/tesseract-ocr/tesseract
![Page 37: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/37.jpg)
How can I use it?
Resources:http://host.robots.ox.ac.uk/pascal/VOC/https://vision.cornell.edu/se3/projects/microsoft-coco
https://adeshpande3.github.io/https://foxrow.com/assets/cnns.pdf
![Page 38: Deep Learning and Computer Vision · 2020-05-01 · Deep Learning and Computer Vision Ryan Fox Milwaukee Machine Learning 12/5/17](https://reader034.vdocuments.mx/reader034/viewer/2022042300/5eca93fd8111a4146101977d/html5/thumbnails/38.jpg)
Ryan FoxEmail: [email protected]: https://foxrow.comTwitter: @ryan_fox
MaleBlack hairSunglasses
No facial hairHappy