Buchumschlag

Guided image generation with conditional invertible neural networks

In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preproces...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ardizzone, Lynton (VerfasserIn) , Lüth, Carsten (VerfasserIn) , Kruse, Jakob (VerfasserIn) , Rother, Carsten (VerfasserIn) , Köthe, Ullrich (VerfasserIn)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: 10 Jul 2019
In: Arxiv
Year: 2019, Pages: 1-11
DOI:10.48550/arXiv.1907.02392
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.1907.02392
Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/1907.02392
Volltext
Verfasserangaben:Lynton Ardizzone, Carsten Lüth, Jakob Kruse, Carsten Rother, Ullrich Köthe

MARC

LEADER 00000caa a2200000 c 4500
001 1810852498
003 DE-627
005 20220820225337.0
007 cr uuu---uuuuu
008 220719s2019 xx |||||o 00| ||eng c
024 7 |a 10.48550/arXiv.1907.02392  |2 doi 
035 |a (DE-627)1810852498 
035 |a (DE-599)KXP1810852498 
035 |a (OCoLC)1341464014 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 28  |2 sdnb 
100 1 |a Ardizzone, Lynton  |d 1994-  |e VerfasserIn  |0 (DE-588)1194988512  |0 (DE-627)1677182296  |4 aut 
245 1 0 |a Guided image generation with conditional invertible neural networks  |c Lynton Ardizzone, Carsten Lüth, Jakob Kruse, Carsten Rother, Ullrich Köthe 
264 1 |c 10 Jul 2019 
300 |a 11 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Gesehen am 19.07.2022 
520 |a In this work, we address the task of natural image generation guided by a conditioning input. We introduce a new architecture called conditional invertible neural network (cINN). The cINN combines the purely generative INN model with an unconstrained feed-forward network, which efficiently preprocesses the conditioning input into useful features. All parameters of the cINN are jointly optimized with a stable, maximum likelihood-based training procedure. By construction, the cINN does not experience mode collapse and generates diverse samples, in contrast to e.g. cGANs. At the same time our model produces sharp images since no reconstruction loss is required, in contrast to e.g. VAEs. We demonstrate these properties for the tasks of MNIST digit generation and image colorization. Furthermore, we take advantage of our bi-directional cINN architecture to explore and manipulate emergent properties of the latent space, such as changing the image style in an intuitive way. 
650 4 |a 68T01 
650 4 |a Computer Science - Computer Vision and Pattern Recognition 
650 4 |a Computer Science - Machine Learning 
700 1 |a Lüth, Carsten  |e VerfasserIn  |0 (DE-588)1262948428  |0 (DE-627)1810862000  |4 aut 
700 1 |a Kruse, Jakob  |d 1990-  |e VerfasserIn  |0 (DE-588)1194989497  |0 (DE-627)1677183136  |4 aut 
700 1 |a Rother, Carsten  |e VerfasserIn  |0 (DE-588)1181464692  |0 (DE-627)1662676883  |4 aut 
700 1 |a Köthe, Ullrich  |e VerfasserIn  |0 (DE-588)123963435  |0 (DE-627)594480884  |0 (DE-576)304484520  |4 aut 
773 0 8 |i Enthalten in  |t Arxiv  |d Ithaca, NY : Cornell University, 1991  |g (2019), Artikel-ID 1907.02392, Seite 1-11  |h Online-Ressource  |w (DE-627)509006531  |w (DE-600)2225896-6  |w (DE-576)28130436X  |7 nnas  |a Guided image generation with conditional invertible neural networks 
773 1 8 |g year:2019  |g elocationid:1907.02392  |g pages:1-11  |g extent:11  |a Guided image generation with conditional invertible neural networks 
856 4 0 |u https://doi.org/10.48550/arXiv.1907.02392  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u http://arxiv.org/abs/1907.02392  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20220719 
993 |a Article 
994 |a 2019 
998 |g 123963435  |a Köthe, Ullrich  |m 123963435:Köthe, Ullrich  |d 700000  |d 708070  |d 700000  |d 728500  |e 700000PK123963435  |e 708070PK123963435  |e 700000PK123963435  |e 728500PK123963435  |k 0/700000/  |k 1/700000/708070/  |k 0/700000/  |k 1/700000/728500/  |p 5  |y j 
998 |g 1181464692  |a Rother, Carsten  |m 1181464692:Rother, Carsten  |d 700000  |d 708070  |d 700000  |d 728500  |e 700000PR1181464692  |e 708070PR1181464692  |e 700000PR1181464692  |e 728500PR1181464692  |k 0/700000/  |k 1/700000/708070/  |k 0/700000/  |k 1/700000/728500/  |p 4 
998 |g 1194989497  |a Kruse, Jakob  |m 1194989497:Kruse, Jakob  |d 700000  |d 708070  |e 700000PK1194989497  |e 708070PK1194989497  |k 0/700000/  |k 1/700000/708070/  |p 3 
998 |g 1262948428  |a Lüth, Carsten  |m 1262948428:Lüth, Carsten  |d 700000  |d 708000  |e 700000PL1262948428  |e 708000PL1262948428  |k 0/700000/  |k 1/700000/708000/  |p 2 
998 |g 1194988512  |a Ardizzone, Lynton  |m 1194988512:Ardizzone, Lynton  |d 110000  |d 700000  |d 728500  |e 110000PA1194988512  |e 700000PA1194988512  |e 728500PA1194988512  |k 0/110000/  |k 0/700000/  |k 1/700000/728500/  |p 1  |x j 
999 |a KXP-PPN1810852498  |e 4170224159 
BIB |a Y 
JSO |a {"name":{"displayForm":["Lynton Ardizzone, Carsten Lüth, Jakob Kruse, Carsten Rother, Ullrich Köthe"]},"origin":[{"dateIssuedKey":"2019","dateIssuedDisp":"10 Jul 2019"}],"id":{"eki":["1810852498"],"doi":["10.48550/arXiv.1907.02392"]},"physDesc":[{"extent":"11 S."}],"relHost":[{"title":[{"title_sort":"Arxiv","title":"Arxiv"}],"part":{"text":"(2019), Artikel-ID 1907.02392, Seite 1-11","extent":"11","year":"2019","pages":"1-11"},"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"pubHistory":["1991 -"],"recId":"509006531","language":["eng"],"type":{"bibl":"edited-book","media":"Online-Ressource"},"disp":"Guided image generation with conditional invertible neural networksArxiv","note":["Gesehen am 28.05.2024"],"id":{"zdb":["2225896-6"],"eki":["509006531"]},"origin":[{"publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]","dateIssuedKey":"1991","publisher":"Cornell University ; Arxiv.org","dateIssuedDisp":"1991-"}],"physDesc":[{"extent":"Online-Ressource"}]}],"person":[{"given":"Lynton","family":"Ardizzone","role":"aut","display":"Ardizzone, Lynton","roleDisplay":"VerfasserIn"},{"role":"aut","roleDisplay":"VerfasserIn","display":"Lüth, Carsten","given":"Carsten","family":"Lüth"},{"family":"Kruse","given":"Jakob","display":"Kruse, Jakob","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Carsten","family":"Rother","role":"aut","display":"Rother, Carsten","roleDisplay":"VerfasserIn"},{"roleDisplay":"VerfasserIn","display":"Köthe, Ullrich","role":"aut","family":"Köthe","given":"Ullrich"}],"title":[{"title_sort":"Guided image generation with conditional invertible neural networks","title":"Guided image generation with conditional invertible neural networks"}],"type":{"bibl":"chapter","media":"Online-Ressource"},"note":["Gesehen am 19.07.2022"],"language":["eng"],"recId":"1810852498"} 
SRT |a ARDIZZONELGUIDEDIMAG1020 

Ähnliche Einträge