lecture 1: introduction to “computer vision”class.vision/96-97/13-face.pdf · deepface closing...
TRANSCRIPT
![Page 1: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/1.jpg)
Lecture 13 -SRTTU – A.Akhavan
Lecture 13:
Face
Alireza Akhavan Pour
۱۳۹۷1اردیبهشت۲۵-سهشنبه
CLASS.VISION
![Page 2: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/2.jpg)
Lecture 13 -SRTTU – A.Akhavan 2 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Face verification vs. face recognitionVerification
• Input image, name/ID
• Output whether the input image is that of the
claimed person
Recognition
• Has a database of K persons
• Get an input image
• Output ID if the image is any of the K persons (or
“not recognized”)
![Page 3: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/3.jpg)
Lecture 13 -SRTTU – A.Akhavan 3 ۱۳۹۷اردیبهشت۲۵–سهشنبه
One-shot learningLearning from one
example to recognize the
person again
![Page 4: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/4.jpg)
Lecture 13 -SRTTU – A.Akhavan 4 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Learning a “similarity” functiond(img1,img2) = degree of difference between images
If d(img1,img2) ≤ 𝜏
> 𝜏
![Page 5: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/5.jpg)
Lecture 13 -SRTTU – A.Akhavan 5 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Siamese network
[Taigman et. al., 2014. DeepFace closing the gap to human level performance]
⋮ ⋮
𝑥(1)
⋮ ⋮
𝑥(2)
![Page 6: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/6.jpg)
Lecture 13 -SRTTU – A.Akhavan 6 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Goal of learning
⋮
f(𝑥(1))
⋮
Parameters of NN define an encoding 𝑓(𝑥 𝑖 )
Learn parameters so that:
If 𝑥 𝑖 , 𝑥 𝑗 are the same person, f 𝑥 𝑖 − f 𝑥 𝑗 2is small.
If 𝑥 𝑖 , 𝑥 𝑗 are different persons, f 𝑥 𝑖 − f 𝑥 𝑗 2is large.
![Page 7: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/7.jpg)
Lecture 13 -SRTTU – A.Akhavan 7 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Learning Objective
[Schroff et al.,2015, FaceNet: A unified embedding for face recognition and clustering]
Anchor Positive Anchor Negative
![Page 8: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/8.jpg)
Lecture 13 -SRTTU – A.Akhavan 8 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Loss function
Training set: 10k pictures of 1k persons
[Schroff et al.,2015, FaceNet: A unified embedding for face recognition and clustering]
![Page 9: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/9.jpg)
Lecture 13 -SRTTU – A.Akhavan 9 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Choosing the triplets A,P,NDuring training, if A,P,N are chosen randomly,
𝑑 𝐴, 𝑃 + 𝛼 ≤ 𝑑(𝐴,𝑁) is easily satisfied.
Choose triplets that’re “hard” to train on.
[Schroff et al.,2015, FaceNet: A unified embedding for face recognition and clustering]
![Page 10: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/10.jpg)
Lecture 13 -SRTTU – A.Akhavan 10 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Training set using triplet lossAnchor Positive Negative
⋮ ⋮ ⋮
![Page 11: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/11.jpg)
Lecture 13 -SRTTU – A.Akhavan 11 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Face verification and binary classification
![Page 12: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/12.jpg)
Lecture 13 -SRTTU – A.Akhavan 12 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Learning the similarity function⋮
f(𝑥(𝑖))
⋮
f(𝑥(𝑗))
𝑥(𝑖)
𝑥(𝑗)
𝑦
[Taigman et. al., 2014. DeepFace closing the gap to human level performance]
![Page 13: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/13.jpg)
Lecture 13 -SRTTU – A.Akhavan 13 ۱۳۹۷اردیبهشت۲۵–سهشنبه
Face verification supervised learning𝑥 𝑦
1
0
0
1
[Taigman et. al., 2014. DeepFace closing the gap to human level performance]
![Page 14: Lecture 1: Introduction to “Computer Vision”class.vision/96-97/13-face.pdf · DeepFace closing the gap to human level performance] SRTTU – A.Akhavan Lecture 13 - 13 ۱۳۹۷تشهبیدرا۲۵–هبنشهس](https://reader034.vdocuments.site/reader034/viewer/2022050208/5f5aaf667fc93e59b62316c6/html5/thumbnails/14.jpg)
Lecture 13 -SRTTU – A.Akhavan
منابع
• https://www.coursera.org/specializations/deep-learning
14 ۱۳۹۷اردیبهشت۱۸-سهشنبه