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
[Journal club] Scalable Diffusion Models with T...
Search
Semantic Machine Intelligence Lab., Keio Univ.
PRO
July 22, 2024
Technology
0
100
[Journal club] Scalable Diffusion Models with Transformers
Semantic Machine Intelligence Lab., Keio Univ.
PRO
July 22, 2024
Tweet
Share
More Decks by Semantic Machine Intelligence Lab., Keio Univ.
See All by Semantic Machine Intelligence Lab., Keio Univ.
Machine Intelligence for Vision, Language, and Actions
keio_smilab
PRO
0
600
[Journal club] V-DPO: Mitigating Hallucination in Large Vision Language Models via Vision-Guided Direct Preference Optimization
keio_smilab
PRO
0
140
[Journal club] Model Alignment as Prospect Theoretic Optimization
keio_smilab
PRO
0
160
[Journal club] DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
keio_smilab
PRO
0
82
[Journal club] LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders
keio_smilab
PRO
2
110
Will multimodal language processing change the world?
keio_smilab
PRO
4
630
[Journal club] MOKA: Open-Vocabulary Robotic Manipulation through Mark-Based Visual Prompting
keio_smilab
PRO
0
200
[Journal club] Seeing the Unseen: Visual Common Sense for Semantic Placement
keio_smilab
PRO
0
190
[Journal club] Language-Embedded Gaussian Splats (LEGS): Incrementally Building Room-Scale Representations with a Mobile Robot
keio_smilab
PRO
0
190
Other Decks in Technology
See All in Technology
Witchcraft for Memory
pocke
1
660
fukabori.fm 出張版: 売上高617億円と高稼働率を陰で支えた社内ツール開発のあれこれ話 / 20250704 Yoshimasa Iwase & Tomoo Morikawa
shift_evolve
PRO
1
140
生まれ変わった AWS Security Hub (Preview) を紹介 #reInforce_osaka / reInforce New Security Hub
masahirokawahara
0
370
生成AI開発案件におけるClineの業務活用事例とTips
shinya337
0
180
作曲家がボカロを使うようにPdMはAIを使え
itotaxi
0
390
mrubyと micro-ROSが繋ぐロボットの世界
kishima
2
380
「Chatwork」の認証基盤の移行とログ活用によるプロダクト改善
kubell_hr
1
240
Node-RED × MCP 勉強会 vol.1
1ftseabass
PRO
0
180
論文紹介:LLMDet (CVPR2025 Highlight)
tattaka
0
240
Snowflake Summit 2025全体振り返り / Snowflake Summit 2025 Overall Review
mtpooh
2
440
asken AI勉強会(Android)
tadashi_sato
0
140
Zephyr RTOSを使った開発コンペに参加した件
iotengineer22
0
140
Featured
See All Featured
Measuring & Analyzing Core Web Vitals
bluesmoon
7
500
Scaling GitHub
holman
459
140k
Facilitating Awesome Meetings
lara
54
6.4k
How to Ace a Technical Interview
jacobian
277
23k
StorybookのUI Testing Handbookを読んだ
zakiyama
30
5.9k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
The MySQL Ecosystem @ GitHub 2015
samlambert
251
13k
Being A Developer After 40
akosma
90
590k
How to train your dragon (web standard)
notwaldorf
94
6.1k
Done Done
chrislema
184
16k
Fantastic passwords and where to find them - at NoRuKo
philnash
51
3.3k
Optimising Largest Contentful Paint
csswizardry
37
3.3k
Transcript
4DBMBCMF%JGGVTJPO.PEFMTXJUI 5SBOTGPSNFST ܚጯٛक़େֶ ਿӜ໌ݚڀࣨ#ീౡେ 8JMMJBN1FFCMFT 4BJOJOH9JF 6$#FSLFMFZ /FX:PSL6OJWFSTJUZ *$$7 8JMMJBN1FFCMFT
4BJOJOH9JFl4DBMBCMF%JGGVTJPO.PEFMTXJUI5SBOTGPSNFSTzJO*$$7 QQ
എܠɿ֦ࢄϞσϧʹΑΔಈը૾ੜ FH 4PSB ͷൃల IUUQTXXXZPVUVCFDPNXBUDI W),Z%"1/@
ؔ࿈ݚڀɿ֦ࢄϞσϧͷόοΫϘʔϯͱͯ͠6/FU͕ଟ༻ • 6/FUͷ.VMUJTDBMFTLJQDPOOFDUJPOTˠ ෆཁͳܭࢉࢿݯͷ༻ 手法 概要 DALL-E 2 [Ramesh+,
22] CLIPを用いてテキストと画像のAlignmentを行う Stable Diffusion [Rombach+, CVPR22] 潜在拡散モデル 6/FU<3POOFCFSHFS .*$$"*> 4UBCMF%JGGVTJPO<3PNCBDI $713>
ఏҊख๏ɿ%JGGVTJPO5SBOTGPSNFS %J5 • જࡏ֦ࢄϞσϧ -%. <3PNCBDI $713>Λϕʔεʹߏங • 7JTJPO5SBOTGPSNFS 7J5
<%PTPWJUTLJZ *$-3>ػߏΛಋೖ • $POEJUJPOJOHʹΑΔ݅ใͷೖྗ
ఏҊख๏ ɿજࡏ֦ࢄϞσϧͱֶͯ͠शͤ͞Δ • ߴ࣍ݩͷըૉۭؒͰ֦ࢄϞσϧΛֶश ͤ͞Δ͜ͱܭࢉྔతʹࠔ • -%.ͱֶͯ͠शͤ͞Δ͜ͱͰ ܭࢉྔΛݮ
• ըૉۭؒͷ֦ࢄϞσϧͰ͋Δ "%.<%IBSJXBM /FVS*14> ͷͷͷ(GMPQTͰֶशՄೳ
ఏҊख๏ ɿೖྗϊΠζΛQBUDIʹղ • "VUPFODPEFS͔ΒಘΒΕͨ /PJTFE-BUFOU YY Λ 7J5ͱಉ༷ʹE࣍ݩͷτʔΫϯ5ʹม •
1BUDIαΠζQΛʹ͢Δͱ5ഒ ʹͳΓUSBOTGPSNFSͷ (GMPQTগͳ͘ͱഒҎ্
ఏҊख๏ ɿ͖݅ೖྗ $POEJUJPOJOH ͷॲཧ • ͖֦݅ࢄϞσϧͰϊΠζΛؚΉը૾ͱͱʹՃใ͕Ճ͑ΒΕΔ FH UJNFTUFQɼΫϥεϥϕϧɼࣗવݴޠ FUD
• ຊݚڀͰ͜ΕΒͷ͖݅ೖྗΛॲཧ͢ΔͨΊʹҎԼͷͭͷҟͳΔઃܭΛఏҊ • *ODPOUFYUDPOEJUJPOJOH • $SPTT"UUFOUJPOCMPDL • "EBQUJWFMBZFSOPSN BEB-/ CMPDL • BEB-/;FSPCMPDL
ఏҊख๏ ɿBEB-/;FSPCMPDL • 7J5ͷTFMGBUUFOUJPOCMPDLʹରͯ͠"EB-/ػߏΛಋೖ • "EB-/ͷεέʔϧ ͓Αͼ ࠩଓͷલͷεέʔϧ
Λύϥϝʔλͱͯ͠Ճ ˠ݅ใΛը૾ʹΑΓڧ͘ө • "EB-/;FSPCMPDLͰͦΕΒΛθϩʹॳظԽ ˠֶशͷॳظஈ֊߃ؔʹ͍ۙಇ͖ ˠ ֶशͷ҆ఆԽ
࣮ݧઃఆ • σʔληοτ • $MBTT$POEJUJPOBM*NBHF/FUY Y<%FOH $713> • ΞʔΩςΫνϟ
• 7J5ͱಉ༷ʹͭͷϞσϧͷେ͖͞ 4 # - 9- Λ༻ҙ • QBUDITJ[FQ • %%1.TBNQMJOHTUFQT • ධՁई • '*% T'*% *4 1SFDJTJPO 3FDBMM • (GMPQT • ֶश • 516WQPE #BUDITJ[F
ఆྔత݁Ռɿ6/FUϕʔεͷख๏Λ্ճͬͨ
ఆੑత݁Ռ • 1BUDITJ[FΛখ͘͞ɼϞσϧΛେ͖͘͢ΔͱΑΓࣗવͳը૾͕ग़ྗ͞ΕΔ ˠ%J5Ͱ(GMPQT͕େ͖͍΄Ͳग़ྗը૾ͷ্࣭͕͕Δ
ࢼ͓ΑͼΤϥʔੳ ఆੑత݁Ռ ɿࣦഊྫ • ಛఆͷMBCFMʹରͯ͠ෆࣗવͳը૾͕ੜ͞ΕΔ • ྫɿJOQVUMBCFM UPZQPPEMF %%1.TBNQMJOHTUFQ
• ϥϕϧʹΑͬͯTUFQͰੜը૾͕ෆ҆ఆˠ ਪ࣌ͷTUFQΛಈతʹมߋ
ॴײ • 4USFOHUI • ֦ࢄϞσϧʹUSBOTGPSNFSΛಋೖ • ܭࢉࢿݯͱग़ྗը૾ͷ࣭ʹ͍ͭͯͷߟ • 8FBLOFTT
• ͕ࣜগͳ͔ͬͨ • Τϥʔੳ͕ͳ͍
·ͱΊ • എܠ • ֦ࢄϞσϧʹΑΔಈը૾ੜ FH 4PSB ͷൃల • ֦ࢄϞσϧʹ͓͚ΔUSBOTGPSNFSͷར༻͕গͳ͍
• ఏҊख๏ • USBOTGPSNFSϕʔεͷ֦ࢄϞσϧͰ͋Δ%JGGVTJPO5SBOTGPSNFS %J5 ΛఏҊ • ݁Ռ • %J5εέʔϥϏϦςΟ͕ߴ͘ɼ(GMPQT͕େ͖͍΄Ͳ'*%͕Լ ˠ ܭࢉࢿݯͱग़ྗը૾ͷ࣭ʹڧ͍૬ؔؔ • %J59-Ϟσϧ͕ɼ$MBTT$POEJUJPOBM*NBHF/FUʹ͓͍ͯ ैདྷͷ6/FUϕʔεͷ֦ࢄϞσϧΛ্ճͬͨ
"QQFOEJYɿ%FOPJTJOH%JGGVTJPO1SPCBCJMJTUJD.PEFM %%1. ֶश
"QQFOEJYɿ$MBTTJGJFSGSFFHVJEBODF • ͖֦݅ࢄϞσϧͰΫϥεϥϕϧΛϥϯμϜʹυϩοϓ ˠ αϯϓϦϯάͷਫ਼Λ্ • #BZFTͷఆཧΑΓ • ֦ࢄϞσϧͷग़ྗΛείΞͱͯ͠ղऍ͢Δͱਪఆ͢ΔϊΠζҎԼͷΑ͏ʹͳΔ
TɿΨΠμϯεεέʔϧ
"QQFOEJYɿ*ODPOUFYUDPOEJUJPOJOH • $POEJUJPOJOHͰ݅ͱͯ͠ೖྗ͞ΕͨτʔΫϯΛ ը૾τʔΫϯͷઌ಄ʹՃ • ͜ΕΒͷτʔΫϯը૾τʔΫϯͱಉ༷ʹѻΘΕɺ 7J5ʣʹ͓͚ΔDMTτʔΫϯͱࣅׂͨΛ࣋ͭ
"QQFOEJYɿ$SPTT"UUFOUJPOCMPDL • 4FMG"UUFOUJPOϒϩοΫͷޙʹ$SPTT"UUFOUJPOΛ Ճͨ͠ઃܭ • <7BTXBOJ /*14>-%.ͱྨࣅͨ͠ΞʔΩςΫνϟ
"QQFOEJYɿ%J5CMPDLEFTJHO • %J59-Ϟσϧʹ͓͍ͯBEB-/;FSPΛ༻͍ͨ ߹͕࠷গͳ͍ܭࢉࢿݯͰ࠷ྑ͍ '*%,είΞΛୡ
"QQFOEJYɿ7JTJPO5SBOTGPSNFS <%PTPWJUTLJZ *$-3>
"QQFOEJYɿ*ODFQUJPO4DPSF *4 • *NBHF/FUͰࣄલֶशࡁΈͷ*ODFQUJPOOFUXPSLΛ༻͍ͨධՁࢦඪ • *ODFQUJPOOFUXPSL͕ࣝผ͘͢͠ɼࣝผ͞ΕΔϥϕϧͷଟ༷ੑ͕͋Δ΄Ͳ େ͖͘ͳΔࢦඪ <4[FHFEZ $713>
"QQFOEJYɿ'SFDIFU*ODFQUJPO%JTUBODF '*% • *NBHF/FUͰࣄલֶशࡁΈͷ*ODFQUJPOOFUXPSLΛ༻͍ͨධՁࢦඪ • ੜ͞Εͨը૾ͷಛ͕(5ը૾ͷಛͱͲͷఔ ࣅ͍ͯΔ͔ΛධՁ͢Δࢦඪ • '*%͕খ͍͞΄Ͳੜ͞Εͨը૾ͷ࣭͕(5ը૾ʹ͍ۙͱߟ͑ΒΕΔ
"QQFOEJYɿ1SFDJTJPO3FDBMM • *NBHF/FUͰࣄલֶशࡁΈͷ7((<4JNPOZBO *$-3>Λ༻͍ͯ ಛϕΫτϧू߹ΛಘΔ
"QQFOEJYɿ(GMPQT • 'MPQTɿුಈখԋࢉͷճ • (GMPQT 'MPQT • ը૾ੜλεΫͰΞʔΩςΫνϟͷෳࡶ͞ΛධՁ͢ΔࡍύϥϝʔλΛ༻͍Δͷ ͕Ұൠత
• ੑೳʹେ͖͘Өڹ͢Δը૾ղ૾ΛҰߟྀ͍ͯ͠ͳ͍ • Ϟσϧͷෳࡶ͞Λද͢ࢦඪͱͯ͠ෆेͳ߹͕͋Δ
"QQFOEJYɿఆྔత݁Ռ
"QQFOEJY(GMPQTͱ'*%ͷ૬ؔ • ΑΓଟ͘ͷ(GMPQTΛͭϞσϧ'*%͕͘ͳΔ
"QQFOEJYɿϞσϧαΠζͱύοναΠζͷݕ౼