東華大學圖書館 |

語系: 繁體中文

說明(常見問題)

回圖書館首頁

手機版館藏查詢

登入

回首頁

切換: 標籤 | MARC模式 | ISBD

Transferable Generative Models.

Jain, Ajay.

FindBook

Google Book

Amazon

博客來

Transferable Generative Models.

紀錄類型:	書目-電子資源 : Monograph/item
正題名/作者:	Transferable Generative Models./
作者:	Jain, Ajay.
出版者:	Ann Arbor : ProQuest Dissertations & Theses, : 2023,
面頁冊數:	134 p.
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:	https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30493292
ISBN:	9798380877213

Transferable Generative Models.
Jain, Ajay.

Transferable Generative Models. - Ann Arbor : ProQuest Dissertations & Theses, 2023 - 134 p.

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

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

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.

ISBN: 9798380877213Subjects--Topical Terms:

523869
Computer science.
Subjects--Index Terms:

3D graphics

Transferable Generative Models.
LDR:02179nmm a2200373 4500 001 2398145
005 20240812064350.5
006 m o d
007 cr#unu||||||||
008 251215s2023 ||||||||||||||||| ||eng d
020 $a 9798380877213
035 $a (MiAaPQ)AAI30493292
035 $a AAI30493292
040 $a MiAaPQ $c MiAaPQ
100 1 $a Jain, Ajay. $3 3768054
245 1 0 $a Transferable Generative Models.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2023
300 $a 134 p.
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.
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.
590 $a School code: 0028.
650 4 $a Computer science. $3 523869
650 4 $a Computer engineering. $3 621879
650 4 $a Information technology. $3 532993
653 $a 3D graphics
653 $a Deep learning
653 $a Text-to-image diffusion model
653 $a Generative AI
690 $a 0984
690 $a 0489
690 $a 0464
710 2 $a University of California, Berkeley. $b Electrical Engineering & Computer Sciences. $3 1671057
773 0 $t Dissertations Abstracts International $g 85-06B.
790 $a 0028
791 $a Ph.D.
792 $a 2023
793 $a English
856 4 0 $u https://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30493292