in introductio ion to
play

In Introductio ion to Deep Learnin ing I2DL: Prof. Niessner, - PowerPoint PPT Presentation

In Introductio ion to Deep Learnin ing I2DL: Prof. Niessner, Prof. Leal-Taix 1 The Team Lecturers Prof. Dr. Laura Prof. Dr. Matthias Leal-Taix Niessner PhDs Patrick Andreas Dendorfer Rssler I2DL: Prof. Niessner, Prof.


  1. In Introductio ion to Deep Learnin ing I2DL: Prof. Niessner, Prof. Leal-Taixé 1

  2. The Team Lecturers Prof. Dr. Laura Prof. Dr. Matthias Leal-Taixé Niessner PhDs Patrick Andreas Dendorfer Rössler I2DL: Prof. Niessner, Prof. Leal-Taixé 2

  3. What is is Computer r Vis ision? First defined in the 60s in artificial intelligence groups • “Mimic the human visual system” • Center block of robotic intelligence • I2DL: Prof. Niessner, Prof. Leal-Taixé 3

  4. Hubel and Wie iesel • David Hubel and Torsten Wiesel were neurobiologists from Harvard Medical School • Experiment revealed several secrets of the human vision system • Won 2 Nobel prizes I2DL: Prof. Niessner, Prof. Leal-Taixé 4

  5. Hubel and Wie iesel Experiment Recorded electrical activity from • individual neurons in the brains of cats. Slide projector to show specific • patterns to the cats noted specific patterns stimulated activity in specific parts of the brain. • Results: Visual cortex cells are sensitive to the orientation of edges but insensitive to their positio n I2DL: Prof. Niessner, Prof. Leal-Taixé 5

  6. I2DL: Prof. Niessner, Prof. Leal-Taixé 6

  7. Few Decades Later … Computer Vision I2DL: Prof. Niessner, Prof. Leal-Taixé 7

  8. Engineering Computer Mathematics science Artificial Robotics Intelligence ML NLP Algorithms Speech Optimization Computer Optics Vision Image Neuroscience processing Physics Biology Psychology I2DL: Prof. Niessner, Prof. Leal-Taixé 8

  9. Im Image Cla lassific ication Pre 2012 I2DL: Prof. Niessner, Prof. Leal-Taixé 9

  10. Im Image Cla lassific ication Awesome A magic box Open the box Become magicians Post 2012 I2DL: Prof. Niessner, Prof. Leal-Taixé 10

  11. Why Deep Learnin ing? I2DL: Prof. Niessner, Prof. Leal-Taixé 11

  12. Deep Learnin ing His istory I2DL: Prof. Niessner, Prof. Leal-Taixé 12

  13. The Empir ire Stri rikes Back 30 25 Deep Learning 20 Approaches 15 10 5 0 2010 2011 2012 2013 2014 Human 2015 2016 2017 AlexNet VGGNet ResNet Ensemble SENet ILSVRC top-5 error on ImageNet I2DL: Prof. Niessner, Prof. Leal-Taixé 13

  14. What Has Changed? MNIST digit • 1998 recognition dataset LeCun 10 7 pixels used in • et al. training 2012 ImageNet image • Krizhevsky recognition dataset 10 14 pixels used in et al. • training I2DL: Prof. Niessner, Prof. Leal-Taixé 14

  15. What Made this is Possible? Big Data Hardware Deep Models know Models are Models are where to learn from trainable complex I2DL: Prof. Niessner, Prof. Leal-Taixé 15

  16. Deep Learnin ing Recognition ACM Turing Award 2019 (Nobel Prize of Computing) Yann LeCun, Geoffrey Hinton, and Yoshua Bengio I2DL: Prof. Niessner, Prof. Leal-Taixé 16

  17. Deep Learnin ing and Computer Vis isio ion Credits: Dr. Pont-Tuset, ETH Zurich I2DL: Prof. Niessner, Prof. Leal-Taixé 17

  18. Deep Learnin ing and Computer Vis isio ion Credits: Dr. Pont-Tuset, ETH Zurich I2DL: Prof. Niessner, Prof. Leal-Taixé 18

  19. Deep Learnin ing Today Object Detection I2DL: Prof. Niessner, Prof. Leal-Taixé 19

  20. Deep Learnin ing Today Self-driving cars I2DL: Prof. Niessner, Prof. Leal-Taixé 20

  21. Deep Learnin ing Today Emoticon suggestion AlphaGo Machine translation I2DL: Prof. Niessner, Prof. Leal-Taixé 21

  22. Deep Learnin ing Today Alpha Star I2DL: Prof. Niessner, Prof. Leal-Taixé 22

  23. Deep Learnin ing Today Automated Text Generation [Karpathy et al.] I2DL: Prof. Niessner, Prof. Leal-Taixé 23

  24. Deep Learnin ing Today Google Assistant (Google IO’19) I2DL: Prof. Niessner, Prof. Leal-Taixé 24

  25. Deep Learnin ing Today Healthcare, cancer detection I2DL: Prof. Niessner, Prof. Leal-Taixé 25

  26. Deep Learnin ing Market […] market research report Deep Learning Market […] “ the deep learning market is expected to be worth USD 1,722. 2.9 Mill llio ion by 20 2022 22. I2DL: Prof. Niessner, Prof. Leal-Taixé 26

  27. Deep Learnin ing Job Pers rspective • Excellent Job Perspectives! – Automation requires ML/DL -> growth! – Top-notch companies will gladly hire you! • Many industries now: – IT-Companies – Cars, Logistic, Health Care, etc… – Manufacturing / Robotics, etc… I2DL: Prof. Niessner, Prof. Leal-Taixé 27

  28. But: : Als lso Challenging! • High-level understanding is not enough – Need proper theory background – Need proper practical skillsets • Can be competitive! – Many good people – Downloading scripts / running code not enough  – Deeper understanding often requires PhDs I2DL: Prof. Niessner, Prof. Leal-Taixé 28

  29. Deep Learnin ing Cult lture I2DL: Prof. Niessner, Prof. Leal-Taixé 29

  30. Deep Learnin ing Memes I2DL: Prof. Niessner, Prof. Leal-Taixé 30

  31. Deep Learnin ing Memes I2DL: Prof. Niessner, Prof. Leal-Taixé 31

  32. Deep Learnin ing Memes I2DL: Prof. Niessner, Prof. Leal-Taixé 32

  33. Deep Learnin ing Memes I2DL: Prof. Niessner, Prof. Leal-Taixé 33

  34. Deep Learnin ing Memes I2DL: Prof. Niessner, Prof. Leal-Taixé 34

  35. Deep Learnin ing Memes I2DL: Prof. Niessner, Prof. Leal-Taixé 35

  36. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé 36

  37. Many TUM Research Labs use DL Visual l Computin ing Lab (P (Pro rof. f. Niessner) r): • – Research in computer vision, graphics, and machine learning Dynamic ic Visio ion and Learn rnin ing Gro roup (Pro rof. f. Leal-Taixe) • – Research on Computer Vision; e.g., video editing/segmentation etc. • 3D Understanding Lab (Dr. Dai): – Research in 3D scenes and its semantics. • Computer Vision Group (Prof. Cremers) – Research in computer vision and pattern recognition Data Mining and Analytics Lab (Prof. Günnemann) • – Research methods for robust machine learning Computer Aided Medical Procedures (Prof. Navab) • – Research in machine learning for medical applications And probably many more  • I2DL: Prof. Niessner, Prof. Leal-Taixé 37

  38. Our r Research Labs • Visual Computing Lab (Prof. Niessner): https://niessnerlab.org/publications.html Twitter: https://twitter.com/MattNiessner – You outu tube: : htt https:/ ://www.y .youtube.com/channel/UCXN2nYjV jVT0 T0cR9G61RPEzK5 K5Q – – Facebook: https://www.facebook.com/matthias.niessner • Dynamic Vision and Learning Lab (Prof. Leal-Taixé): https://dvl.in.tum.de/publications.html – Twitter: https://twitter.com/lealtaixe – Youtube: https://www.youtube.com/channel/UCQVCsX1CcZQr0oUMZg6szIQ I2DL: Prof. Niessner, Prof. Leal-Taixé 38

  39. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Caelles et al., CVPR’ 17] One -Shot Video Object Segmentation 39

  40. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Dosovitskiy et al., ICCV’ 15] FlowNet 40

  41. Deep Learnin ing at TUM CC3 CC2 CC1 Reshape Conv+BN+ReLU Pooling Upsample Concat Score DDFF [Hazirbas et al., IJCV’18] Deep Depth From Focus. I2DL: Prof. Niessner, Prof. Leal-Taixé 41

  42. Deep Learnin ing at TUM • Video anonymization Control identity Source [Maximov et al., CVPR 2020] CIAGAN: Conditional identity I2DL: Prof. Niessner, Prof. Leal-Taixé anonymization generative adversarial networks. 42

  43. Deep Learnin ing at TUM • Multiple object tracking with graph neural networks [Brasó and Leal-Taixé, CVPR 2020] Learning a Neural Solver for I2DL: Prof. Niessner, Prof. Leal-Taixé Multiple Object Tracking. 43

  44. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Yang et al., ECCV’ 18] Deep Virtual Stereo Odometry 44

  45. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Xie et al. Siggraph ’ 18] tempoGAN 45

  46. Deep Learnin ing at TUM ScanNet Stats: -Kinect-style RGB-D sensors -1513 scans of 3D environments -2.5 Mio RGB-D frames -Dense 3D, crowd-source MTurk labels -Annotations projected to 2D frames I2DL: Prof. Niessner, Prof. Leal-Taixé [Dai et al., CVPR’17] ScanNet 47

  47. Deep Learnin ing at TUM [Hou et al., CVPR’19] 3D Semantic Instance Segmentation I2DL: Prof. Niessner, Prof. Leal-Taixé 48

  48. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Thies et al., Siggraph’19 ]: Neural Textures 49

  49. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Thies et al., Siggraph’19 ]: Neural Textures 50

  50. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Thies et al., Siggraph’19 ]: Neural Textures 51

  51. Deep Learnin ing at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé [Thies et al., Siggraph’19 ]: Neural Textures 52

  52. Deep Learnin ing at TUM [Roessler et al., ICCV’19 ]: Face Forensics++ I2DL: Prof. Niessner, Prof. Leal-Taixé 53

  53. Context of Other Lectures at TUM I2DL: Prof. Niessner, Prof. Leal-Taixé 54

  54. Machine Learning Optimization basics Introduction Introduction to to Deep NN Learning CNN Back- propagation RNN I2DL: Prof. Niessner, Prof. Leal-Taixé 55

Recommend


More recommend