Tweet
Tweet

Slide 1

Slide 1 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto Encoder +  ∩deep learning∩    March 15, 2019 Katsunori Ohnishi DeNA Co., Ltd. 1

Slide 2

Slide 2 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n  n Unsupervised feature learning with deep generative model  Variational Auto-Encoder  Adversarial feature learning n  2

Slide 3

Slide 3 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n +> TS ( ) U Twitter: @0hnishi , speakerdeck: https://speakerdeck.com/katsunoriohnishi n 6P U 2014,4/-2017,9/: B4~M2.509+7Computer VisionGH KAM • 3L (8QC@): CVPR16 (spotlight oral), ACMMM16, AAAI18 (oral) U RN: http://katsunoriohnishi.github.io/ U 2017,10/-

Slide 4

Slide 4 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n 26 +7∩deep learning∩&.# $3951.!" 4 (-4%,*() 26 1. 395: >< Kaggle8)%  VAE/'0   0

Slide 5

Slide 5 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n 8<0=∩deep learning∩+3'$(9?;73%"!#& 5 ( 2:*1/-) 8<$ 73  9?; @>< Kaggle>.*  VAE5,6  6 9)4 

Slide 6

Slide 6 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Auto-encoder n  encoder-decoder &"  6 $' loss ! Mean Squared Error(MSE) Self-supervised learning % #  https://hackernoon.com/a-deep-convolutional-denoising-autoencoder-for-image-classification-26c777d3b88e

Slide 7

Slide 7 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Auto-encoder  7 Output!mask   segmentation “Auto” encoder-decoder'%)MNA> Segmentation Auto-encoder.48O encoder!=:K *G(&) %$→CG(&) "#3  Pre-training MSE

Slide 8

Slide 8 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Auto-encoder n Pre-training: C 7%59 C Test $∩ train  … 5> n Noise=; 0  n Anomaly detection18.?*6 n &(A<3)/',)!+/ C MSE 4B#8. "@&-2!  8

Slide 9

Slide 9 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder 9 Auto-encoder Variational Auto-encoder       

Slide 10

Slide 10 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n $("!#.*"!#- 2  1)encoder-decoder$("!# +0 $(   %,&.*"!# '/"!#  10 https://stanford.edu/~shervine/teaching/cs-229/cheatsheet-supervised-learning

Slide 11

Slide 11 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n VAE ( #$'!   (  &   z  %" 11

Slide 12

Slide 12 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n     12  https://qiita.com/kenmatsu4/i tems/b029d697e9995d93aa24 

Slide 13

Slide 13 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n      13      https://qiita.com/kenmatsu4/i tems/b029d697e9995d93aa24

Slide 14

Slide 14 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n 5,-#"3  14 /+45,0.   *! +4&!1' 5,0( +4 2 $%)1' https://hackernoon.com/latent-space-visualization-deep-learning-bits-2-bd09a46920df

Slide 15

Slide 15 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n Q:VAE#!=-0$2":6  ? A: ' 15 ()/":) &4":713.5>+":     VAE#!=-.*→output;*9,"713.5  8%< )/":( Tutorial on Variational Autoencoders [C. Doersch, arxiv15]

Slide 16

Slide 16 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n  predict/train         16

Slide 17

Slide 17 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n Forward"  !  17 ! " Σ " z Input X output Y Sample $ from % ! " , Σ "  z  #  backward

Slide 18

Slide 18 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n    18 ! " Σ " z Input X output Y Sample $ from % Ο, Ι ∗ + Forward Backward

Slide 19

Slide 19 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n Loss 19 ! " Σ " z Input X output Y Sample $ from % Ο, Ι ∗ + + − " - ./ %(!("), 2("))||% Ο, Ι KL !* q(z|X) &X $,6'logp(X|z) +/0 − (%&, *KL ! -.#2 1'4  *5') "30

Slide 20

Slide 20 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n 7459JG;? L Q: -/'.$+'!# … L A: MSE=E!  20 DF,/0'> H3<9β"  KL)$,&%0' q(z|X) 5 *(X 29K6logp(X|z) 8@C − 7459 KL)$,&%0' A:IB (e.g. MSE) c β # − $ % A:*(:*( 6 →1 1: *( 8@

Slide 21

Slide 21 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n      ! /    • https://arxiv.org/pdf/1606.05908.pdf • https://qiita.com/kenmatsu4/items/b029d697e9995d93aa24 21 − 

Slide 22

Slide 22 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n   22   https://qiita.com/kenmatsu4/i tems/b029d697e9995d93aa24

Slide 23

Slide 23 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n :       23 ! " Σ " z Input X output Y Sample $ from % Ο, Ι ∗ +  c

Slide 24

Slide 24 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n  +36 AEVAE'. 7 5,-)$1/%  24 AE!4 5,-)$1  #0*2&( " VAE https://qiita.com/kenmatsu4/i tems/b029d697e9995d93aa24

Slide 25

Slide 25 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n :>4   B */DL&%&'15example- • Chainer: https://github.com/chainer/chainer/tree/master/examples/vae • Pytorch: https://github.com/pytorch/examples/tree/master/vae • Keras: https://github.com/keras-team/keras/blob/master/examples/variational_autoencoder.py B Tips • " !)+,=3< • A67.(0?  #$&2 • 0?@9  8; 25

Slide 26

Slide 26 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Variational Auto-encoder n $,(+#&2018%*"&(*%)"'%A! … K −"#$ −β    26 pytorch [Kingma+, ICLR14]     J=?/ 7>-G: 9;H@ :;H .6    CB< F https://github.com/pytorch/examples/blob/master/vae/main.py e.g.) D9IE 543 

Slide 27

Slide 27 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. GAN n VAE     MSE Loss    GAN     27 https://skymind.ai/wiki/generative-adversarial-network-gan

Slide 28

Slide 28 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. GAN n Discriminator#+1,3/ )- 5 "$( %'  28  real/fake0*  discriminator !24,3/& . ,3/ UCF101 Chance 0.9 unsupervised VGAN [C. Vondrick+, NIPS16] 36.7 FTGAN [K. Ohnishi+, AAAI18] 60.9 supervised Two-stream [K. Simonyan+, NIPS14] 88.0 I3D [J. Carreira+ CVPR17] 98.0 CIFAR10 Chance 10.0 unsupervised DCGAN [A. Radford+, ICLR16] 82.8 supervised Alexnet [A. Krizhevsky+, NIPS12] 89.0 Resnet110 [K. He+, CVPR16] 93.6 Accuracy

Slide 29

Slide 29 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n GeneratorEncoderadversarial training     G: z (uniform distribution)   G(z)   E:  x E(x)  29 BiGAN

Slide 30

Slide 30 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n GeneratorEncoderadversarial training     G: z (uniform distribution)   G(z)   E:  x E(x)  30 generated data e.g.) uniform distribution BiGAN

Slide 31

Slide 31 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n GeneratorEncoderadversarial training     G: z (uniform distribution)   G(z)   E:  x E(x)  31 real data generated data e.g.) uniform distribution BiGAN

Slide 32

Slide 32 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n GeneratorEncoderadversarial training     G: z (uniform distribution)   G(z)   E:  x E(x)  32 real data generated data e.g.) uniform distribution generated feature BiGAN

Slide 33

Slide 33 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n  33 GAN BiGAN xG(z) Dreal fake  • x: real data • G(z):  {x, E(x)}{G(z), z} D • x: real data • E(x): real data   • z: random noise • G(z) : 

Slide 34

Slide 34 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n  34

Slide 35

Slide 35 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n  35   

Slide 36

Slide 36 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. Adversarial feature learning [J. Donahue+ ICLR17] n   : https://github.com/jeffdonahue/bigan   pytorch( ): https://github.com/9310gaurav/ali-pytorch 36

Slide 37

Slide 37 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. VAEBiGAN  37 n VAE > -:7<+0*  > #'(23 61 > Encoder, Decoder$! "%7<+#  > )89  n BiGAN > -:.0* > #'(23 61 > Encoder, Generator, Discriminator$! "%/61 > 5;=&,+GAN 4

Slide 38

Slide 38 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved.  n VAE;ME LF n -13HEnd2End$#"64,9!&8G ) @   38

Slide 39

Slide 39 text

Copyright (C) 2019 DeNA Co.,Ltd. All Rights Reserved. FAQ n $#LGDO93;31Ca!S"'*)_W9 3;' b _W * IFXK_W93;E @`F_WUH? b IFYVC >B n Kaggle 0=8VAEVNU? J^) b \ #AENU? )'VAEV &(NU? )T+*) n VAE! A -  b !524</Z] >B31#,PQ!% b AE,VAE)&( R b 6.7:#! M[!% 39