Upgrade to Pro
— share decks privately, control downloads, hide ads and more …
Speaker Deck
Features
Speaker Deck
PRO
Sign in
Sign up for free
Search
Search
Deep Learning Image Manipulation
Search
Leszek Rybicki
May 18, 2017
Research
2
190
Deep Learning Image Manipulation
Illustrated guide to some image manipulation methods, with demonstration.
Leszek Rybicki
May 18, 2017
Tweet
Share
More Decks by Leszek Rybicki
See All by Leszek Rybicki
Let's talk about Fakes
lunardog
0
96
How to Patch Image Classifiers
lunardog
0
1.7k
Towards Realistic Predictors - EN
lunardog
0
1.6k
Towards Realistic Predictors
lunardog
1
2k
Deep Learning Hot Dog Detector
lunardog
0
230
Finding beans in burgers: paper reading notes
lunardog
0
1.2k
Kelner: Serve Your Models
lunardog
0
100
Image Analysis at Cookpad
lunardog
1
1.5k
Kelner: serve your models
lunardog
1
330
Other Decks in Research
See All in Research
TransformerによるBEV Perception
hf149
1
380
Weekly AI Agents News! 9月号 論文のアーカイブ
masatoto
1
100
Practical The One Person Framework
asonas
1
1.4k
FOSS4G 山陰 Meetup 2024@砂丘 はじめの挨拶
wata909
1
110
marukotenant01/tenant-20240826
marketing2024
0
510
20240725異文化融合研究セミナーiSeminar
tadook
0
150
20240820: Minimum Bayes Risk Decoding for High-Quality Text Generation Beyond High-Probability Text
de9uch1
0
100
Embers of Autoregression: Understanding Large Language Models Through the Problem They are Trained to Solve
eumesy
PRO
6
1.1k
12
0325
0
110
[第62回NLPコロキウム]「なりきり」を促すHCI設計:対話型接客ロボットの遠隔操作者へのリアルタイム変換音声フィードバックの適用
nami_ogawa
0
300
MetricSifter:クラウドアプリケーションにおける故障箇所特定の効率化のための多変量時系列データの特徴量削減 / FIT 2024
yuukit
2
110
熊本から日本の都市交通政策を立て直す~「車1割削減、渋滞半減、公共交通2倍」の実現へ~@公共交通マーケティング研究会リスタートセミナー
trafficbrain
0
120
Featured
See All Featured
Producing Creativity
orderedlist
PRO
341
39k
A better future with KSS
kneath
238
17k
What's new in Ruby 2.0
geeforr
342
31k
Designing for humans not robots
tammielis
249
25k
XXLCSS - How to scale CSS and keep your sanity
sugarenia
246
1.3M
[Rails World 2023 - Day 1 Closing Keynote] - The Magic of Rails
eileencodes
32
1.8k
[RailsConf 2023] Rails as a piece of cake
palkan
51
4.9k
CoffeeScript is Beautiful & I Never Want to Write Plain JavaScript Again
sstephenson
159
15k
Sharpening the Axe: The Primacy of Toolmaking
bcantrill
37
1.8k
How to Ace a Technical Interview
jacobian
275
23k
The Myth of the Modular Monolith - Day 2 Keynote - Rails World 2024
eileencodes
14
1.9k
The Invisible Side of Design
smashingmag
297
50k
Transcript
%FFQ-FBSOJOH *NBHF.BOJQVMBUJPO BOJMMVTUSBUFEHVJEF .-,JUDIFO
"CPVUNF w -FT[FL3ZCJDLJ w HJUIVC!MVOBSEPH w CPSOJO1PMBOE w .-3FTFBSDIFSBU$PPLQBE w
*MJLFOBUUP
DBSFFST!DPPLQBEDPN 8BOUUPXPSLXJUIVT
$POWPMVUJPOBM "SJUINFUJD OCIKE
*NBHFTUPGFBUVSFT
$POWPMVUJPO http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html input output input output kernel
4USJEF http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html 2px 2px 2px 2px
1BEEJOH http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html 2px 2px
4USJEF QBEEJOH http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html
5SBOTQPTFE http://deeplearning.net/software/theano/tutorial/conv_arithmetic.html simulated here with padding also called “deconvolution” “fractional
stride”
%PXOTBNQMJOH features or small resolution image convolutional layer or layers
RGB image input output
6QTBNQMJOH upsampling CNN layer or layers RGB image features or
small resolution image input output
&ODPEFS%FDPEFS D E image in Decoder Encoder image out feature
space
'VMMZ$POOFDUFE $MBTTJpFS approve loan reject class data or features also
called “Dense” layer
$//$MBTTJpFS food person plant other AlexNet, LeNet, VGG…
'PPE/FU ™ food not food
@teenybiscuit
None
@teenybiscuit
@teenybiscuit
@teenybiscuit
@teenybiscuit
@teenybiscuit
(FOFSBUJWF "EWFSTBSJBM /FUXPSLT
Generator Discriminator https://speakerdeck.com/lunardog/deep-convolutional-voight-kampf-test “Couple of bots studying for the Turing
Test”
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec
Radford, Luke Metz, Soumith Chintala (Submitted on 19 Nov 2015 (v1), last revised 7 Jan 2016 (this version, v2)) https://arxiv.org/abs/1511.06434
Generator Discriminator G MPPLTMFHJU UPUBMMZTIPQQFE D
G SFBM GBLF D D(G(noise)) ˠ real (FOFSBUPSUSBJOJOH Discriminator acts
as the teacher
G SFBM GBLF D SFBM GBLF D D(G(noise)) ˠ fake
D(photo) ˠ real %JTDSJNJOBUPSUSBJOJOH Generator provides negative examples
None
https://www.youtube.com/watch?v=rs3aI7bACGc ©Yota Ishida
Unsupervised Representation Learning with Deep Convolutional Generative Adversarial Networks Alec
Radford, Luke Metz, Soumith Chintala (Submitted on 19 Nov 2015 (v1), last revised 7 Jan 2016 (this version, v2)) https://arxiv.org/abs/1511.06434
$POEJUJPOBM ("/T
G NBMF GFNBMF DIJME FMEFSMZ G(noise | conditions) $POEJUJPOBM(FOFSBUPS
SJHIU XSPOH NBMF GFNBMF DIJME FMEFSMZ D $POEJUJPOBM%JTDSJNJOBUPS
SJHIU XSPOH NBMF GFNBMF DIJME FMEFSMZ D SJHIU XSPOH NBMF
GFNBMF DIJME FMEFSMZ SJHIU XSPOH NBMF GFNBMF DIJME FMEFSMZ D D
SJHIU XSPOH D $POEJUJPOBM("/ https://arxiv.org/abs/1411.1784 Conditional Generative Adversarial Nets Mehdi
Mirza, Simon Osindero (Submitted on 6 Nov 2014) Generator Discriminator NBMF GFNBMF DIJME FMEFSMZ G NBMF GFNBMF DIJME FMEFSMZ same condition
G NBMF GFNBMF DIJME FMEFSMZ SJHIU XSPOH NBMF GFNBMF DIJME
FMEFSMZ D $POEJUJPOBM("/ Discriminator Generator
https://www.faceapp.com/ Disclaimer: FaceApp authors don’t disclose their method. This is
only my guess. It may have nothing to do with GANs. original
original https://www.faceapp.com/
https://www.faceapp.com/ original
"SUJTUJD4UZMF5SBOTGFS Improved!
https://prisma-ai.com/
https://prisma-ai.com/ https://prisma-ai.com/
https://prisma-ai.com/ https://prisma-ai.com/
https://prisma-ai.com/ https://prisma-ai.com/
https://arxiv.org/abs/1603.08155 transformation network loss network Gram matrices in feature space
pre-trained content image style image
“Gram matrices in feature space” https://en.wikipedia.org/wiki/Gramian_matrix
https://www.youtube.com/watch?v=xVJwwWQlQ1o
$ZDMF("/
https://github.com/junyanz/CycleGAN
https://github.com/junyanz/CycleGAN
https://github.com/junyanz/CycleGAN
(FOFSBUPS transformation network https://arxiv.org/abs/1603.08155
GBLF IPSTF GBLF IPSTF … %JTDSJNJOBUPS fully convolutional judges patches
of the input image https://arxiv.org/abs/1603.08155
"EWFSTBSJBM-PTT X F G Y GBLF [FCSB GBLF [FCSB …
GBLF IPSTF GBLF IPSTF … X(F(horse)) ˠ classify as zebra Y(F(zebra)) ˠ classify as horse
$ZDMF-PTT G F G(F(image))ˠ the same image F G F(G(image))ˠ
the same image
https://www.youtube.com/watch?v=9reHvktowLY
5IF&OE