Variational Auto Encoder入門

Slide 1

Slide 1 text

Slide 2

Slide 2 text

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 VisionGHKAM • 3L (8QC@): CVPR16 (spotlight oral), ACMMM16, AAAI18 (oral) U RN: http://katsunoriohnishi.github.io/ U 2017,10/-

Slide 4

Slide 4 text

Slide 5

Slide 5 text

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

Slide 9

Slide 9 text

Slide 10

Slide 10 text

Slide 11

Slide 11 text

Slide 12

Slide 12 text

Slide 13

Slide 13 text

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

Slide 17

Slide 17 text

Slide 18

Slide 18 text

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 ! -.#21'4 *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

Slide 22

Slide 22 text

Slide 23

Slide 23 text

Slide 24

Slide 24 text

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

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

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

Slide 32

Slide 32 text

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

Slide 35

Slide 35 text

Slide 36

Slide 36 text

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;=&,+GAN4

Slide 38

Slide 38 text

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