國立虎尾科技大學 |

Transferable Generative Models.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	Transferable Generative Models./
作者:	Jain, Ajay.
面頁冊數:	1 online resource (134 pages)
附註:	Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
Contained By:	Dissertations Abstracts International85-06B.
標題:	Computer science. -
電子資源:	click for full text (PQDT)
ISBN:	9798380877213

Transferable Generative Models.
Jain, Ajay.

Transferable Generative Models. - 1 online resource (134 pages)

Source: Dissertations Abstracts International, Volume: 85-06, Section: B.

Thesis (Ph.D.)--University of California, Berkeley, 2023.

Includes bibliographical references

We present progress in developing stable, scalable and transferable generative models for visual data. We first learn expressive image priors using autoregressive models which generate high-quality and diverse images. We then explore transfer learning to generalize visual representations models to new data modalities with limited available data. We propose two methods to generate high quality 3D graphics from sparse input images or natural language descriptions by distilling knowledge from pretrained discriminative vision models. We briefly summarize our work on improving generation quality with a Denoising Diffusion Probabilistic Model, and demonstrate how to transfer it to new modalities including high-quality text-to-3D synthesis using Score Distillation Sampling. Finally, we generate 2D vector graphics from text by optimizing a vector graphics renderer with knowledge distilled from a pretrained text-to-image diffusion model, without vector graphics data. Our models enable high-quality generation across many modalities, and continue to be broadly applied in subsequent work.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798380877213Subjects--Topical Terms:

573171
Computer science.
Subjects--Index Terms:

3D graphicsIndex Terms--Genre/Form:

554714
Electronic books.

Transferable Generative Models.
LDR:02403ntm a22003857 4500 001 1146241
005 20240812064350.5
006 m o d
007 cr bn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798380877213
035 $a (MiAaPQ)AAI30493292
035 $a AAI30493292
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Jain, Ajay. $3 1471599
245 1 0 $a Transferable Generative Models.
264 0 $c 2023
300 $a 1 online resource (134 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Dissertations Abstracts International, Volume: 85-06, Section: B.
500 $a Advisor: Abbeel, Pieter.
502 $a Thesis (Ph.D.)--University of California, Berkeley, 2023.
504 $a Includes bibliographical references
520 $a We present progress in developing stable, scalable and transferable generative models for visual data. We first learn expressive image priors using autoregressive models which generate high-quality and diverse images. We then explore transfer learning to generalize visual representations models to new data modalities with limited available data. We propose two methods to generate high quality 3D graphics from sparse input images or natural language descriptions by distilling knowledge from pretrained discriminative vision models. We briefly summarize our work on improving generation quality with a Denoising Diffusion Probabilistic Model, and demonstrate how to transfer it to new modalities including high-quality text-to-3D synthesis using Score Distillation Sampling. Finally, we generate 2D vector graphics from text by optimizing a vector graphics renderer with knowledge distilled from a pretrained text-to-image diffusion model, without vector graphics data. Our models enable high-quality generation across many modalities, and continue to be broadly applied in subsequent work.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Computer science. $3 573171
650 4 $a Computer engineering. $3 569006
650 4 $a Information technology. $3 559429
653 $a 3D graphics
653 $a Deep learning
653 $a Text-to-image diffusion model
653 $a Generative AI
655 7 $a Electronic books. $2 local $3 554714
690 $a 0984
690 $a 0489
690 $a 0464
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a University of California, Berkeley. $b Electrical Engineering & Computer Sciences. $3 845564
773 0 $t Dissertations Abstracts International $g 85-06B.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30493292 $z click for full text (PQDT)