Buchumschlag

Network-to-network translation with conditional invertible neural networks

Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation. Recent work suggests that the power of these massive models is captured by the representati...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Rombach, Robin (VerfasserIn) , Esser, Patrick (VerfasserIn) , Ommer, Björn (VerfasserIn)
Dokumenttyp: Article (Journal) Kapitel/Artikel
Sprache:Englisch
Veröffentlicht: 9 Nov 2020
Ausgabe:Version v2
In: Arxiv
Year: 2020, Pages: 1-24
DOI:10.48550/arXiv.2005.13580
Online-Zugang:Verlag, lizenzpflichtig, Volltext: https://doi.org/10.48550/arXiv.2005.13580
Verlag, lizenzpflichtig, Volltext: http://arxiv.org/abs/2005.13580
Volltext
Verfasserangaben:Robin Rombach, Patrick Esser, Björn Ommer

MARC

LEADER 00000caa a2200000 c 4500
001 1818127288
003 DE-627
005 20230118164535.0
007 cr uuu---uuuuu
008 221006s2020 xx |||||o 00| ||eng c
024 7 |a 10.48550/arXiv.2005.13580  |2 doi 
035 |a (DE-627)1818127288 
035 |a (DE-599)KXP1818127288 
035 |a (OCoLC)1361714916 
040 |a DE-627  |b ger  |c DE-627  |e rda 
041 |a eng 
084 |a 27  |2 sdnb 
100 1 |a Rombach, Robin  |e VerfasserIn  |0 (DE-588)1269607952  |0 (DE-627)1818109115  |4 aut 
245 1 0 |a Network-to-network translation with conditional invertible neural networks  |c Robin Rombach, Patrick Esser, Björn Ommer 
250 |a Version v2 
264 1 |c 9 Nov 2020 
300 |a 24 
336 |a Text  |b txt  |2 rdacontent 
337 |a Computermedien  |b c  |2 rdamedia 
338 |a Online-Ressource  |b cr  |2 rdacarrier 
500 |a Version 1 vom 27. Mai 2020, Version 2 vom 9. November 2020 
500 |a Gesehen am 06.10.2022 
520 |a Given the ever-increasing computational costs of modern machine learning models, we need to find new ways to reuse such expert models and thus tap into the resources that have been invested in their creation. Recent work suggests that the power of these massive models is captured by the representations they learn. Therefore, we seek a model that can relate between different existing representations and propose to solve this task with a conditionally invertible network. This network demonstrates its capability by (i) providing generic transfer between diverse domains, (ii) enabling controlled content synthesis by allowing modification in other domains, and (iii) facilitating diagnosis of existing representations by translating them into interpretable domains such as images. Our domain transfer network can translate between fixed representations without having to learn or finetune them. This allows users to utilize various existing domain-specific expert models from the literature that had been trained with extensive computational resources. Experiments on diverse conditional image synthesis tasks, competitive image modification results and experiments on image-to-image and text-to-image generation demonstrate the generic applicability of our approach. For example, we translate between BERT and BigGAN, state-of-the-art text and image models to provide text-to-image generation, which neither of both experts can perform on their own. 
650 4 |a Computer Science - Computer Vision and Pattern Recognition 
650 4 |a Computer Science - Machine Learning 
700 1 |a Esser, Patrick  |e VerfasserIn  |0 (DE-588)1116611430  |0 (DE-627)870571214  |0 (DE-576)478524323  |4 aut 
700 1 |a Ommer, Björn  |d 1981-  |e VerfasserIn  |0 (DE-588)1034893106  |0 (DE-627)746457510  |0 (DE-576)382507916  |4 aut 
773 0 8 |i Enthalten in  |t Arxiv  |d Ithaca, NY : Cornell University, 1991  |g (2020), Artikel-ID 2005.13580, Seite 1-24  |h Online-Ressource  |w (DE-627)509006531  |w (DE-600)2225896-6  |w (DE-576)28130436X  |7 nnas  |a Network-to-network translation with conditional invertible neural networks 
773 1 8 |g year:2020  |g elocationid:2005.13580  |g pages:1-24  |g extent:24  |a Network-to-network translation with conditional invertible neural networks 
856 4 0 |u https://doi.org/10.48550/arXiv.2005.13580  |x Verlag  |x Resolving-System  |z lizenzpflichtig  |3 Volltext 
856 4 0 |u http://arxiv.org/abs/2005.13580  |x Verlag  |z lizenzpflichtig  |3 Volltext 
951 |a AR 
992 |a 20221006 
993 |a Article 
994 |a 2020 
998 |g 1034893106  |a Ommer, Björn  |m 1034893106:Ommer, Björn  |d 700000  |d 708070  |d 700000  |d 728500  |e 700000PO1034893106  |e 708070PO1034893106  |e 700000PO1034893106  |e 728500PO1034893106  |k 0/700000/  |k 1/700000/708070/  |k 0/700000/  |k 1/700000/728500/  |p 3  |y j 
998 |g 1116611430  |a Esser, Patrick  |m 1116611430:Esser, Patrick  |d 700000  |d 708070  |e 700000PE1116611430  |e 708070PE1116611430  |k 0/700000/  |k 1/700000/708070/  |p 2 
998 |g 1269607952  |a Rombach, Robin  |m 1269607952:Rombach, Robin  |d 700000  |d 708000  |d 700000  |d 728500  |e 700000PR1269607952  |e 708000PR1269607952  |e 700000PR1269607952  |e 728500PR1269607952  |k 0/700000/  |k 1/700000/708000/  |k 0/700000/  |k 1/700000/728500/  |p 1  |x j 
999 |a KXP-PPN1818127288  |e 4194787641 
BIB |a Y 
JSO |a {"recId":"1818127288","language":["eng"],"type":{"bibl":"chapter","media":"Online-Ressource"},"note":["Version 1 vom 27. Mai 2020, Version 2 vom 9. November 2020","Gesehen am 06.10.2022"],"title":[{"title":"Network-to-network translation with conditional invertible neural networks","title_sort":"Network-to-network translation with conditional invertible neural networks"}],"person":[{"role":"aut","roleDisplay":"VerfasserIn","display":"Rombach, Robin","given":"Robin","family":"Rombach"},{"family":"Esser","given":"Patrick","display":"Esser, Patrick","roleDisplay":"VerfasserIn","role":"aut"},{"given":"Björn","family":"Ommer","role":"aut","roleDisplay":"VerfasserIn","display":"Ommer, Björn"}],"relHost":[{"physDesc":[{"extent":"Online-Ressource"}],"origin":[{"publisherPlace":"Ithaca, NY ; [Erscheinungsort nicht ermittelbar]","publisher":"Cornell University ; Arxiv.org","dateIssuedKey":"1991","dateIssuedDisp":"1991-"}],"id":{"zdb":["2225896-6"],"eki":["509006531"]},"disp":"Network-to-network translation with conditional invertible neural networksArxiv","type":{"bibl":"edited-book","media":"Online-Ressource"},"note":["Gesehen am 28.05.2024"],"recId":"509006531","language":["eng"],"pubHistory":["1991 -"],"part":{"text":"(2020), Artikel-ID 2005.13580, Seite 1-24","extent":"24","year":"2020","pages":"1-24"},"titleAlt":[{"title":"Arxiv.org"},{"title":"Arxiv.org e-print archive"},{"title":"Arxiv e-print archive"},{"title":"De.arxiv.org"}],"title":[{"title_sort":"Arxiv","title":"Arxiv"}]}],"physDesc":[{"extent":"24 S."}],"id":{"eki":["1818127288"],"doi":["10.48550/arXiv.2005.13580"]},"origin":[{"dateIssuedDisp":"9 Nov 2020","dateIssuedKey":"2020","edition":"Version v2"}],"name":{"displayForm":["Robin Rombach, Patrick Esser, Björn Ommer"]}} 
SRT |a ROMBACHROBNETWORKTON9202 

Ähnliche Einträge