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
[読み会]Not All Tokens Are Equal: Human-centric Vi...
Search
Kei Moriyama
January 08, 2024
0
51
[読み会]Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
Kei Moriyama
January 08, 2024
Tweet
Share
More Decks by Kei Moriyama
See All by Kei Moriyama
[Human-AI Decision Making勉強会] 正確に予測できるAIは人間の意思決定を助けるか?
keimoriyama
0
360
Featured
See All Featured
Leadership Guide Workshop - DevTernity 2021
reverentgeek
1
200
How To Stay Up To Date on Web Technology
chriscoyier
791
250k
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
280
Facilitating Awesome Meetings
lara
57
6.8k
Building a Modern Day E-commerce SEO Strategy
aleyda
45
8.7k
Building Better People: How to give real-time feedback that sticks.
wjessup
370
20k
The Director’s Chair: Orchestrating AI for Truly Effective Learning
tmiket
1
99
"I'm Feeling Lucky" - Building Great Search Experiences for Today's Users (#IAC19)
danielanewman
231
22k
My Coaching Mixtape
mlcsv
0
50
Leo the Paperboy
mayatellez
4
1.4k
Designing Dashboards & Data Visualisations in Web Apps
destraynor
231
54k
Claude Code のすすめ
schroneko
67
210k
Transcript
Not All Tokens Are Equal: Human-centric Visual Analysis via Token
Clustering Transformer @1/10 山
จใ CVPR 20 22
จ֓ཁ Vision Transformer Attention 手
ݚڀͷཱͪҐஔ ViT 長 方 行
ݚڀͷཱͪҐஔ ViT 長 方 行 目
ݚڀͷཱͪҐஔ ViT 長 方 行 人
ݚڀͷఏҊ ViT CTM
ݚڀͷఏҊ MTA Head
ఏҊख๏1ɿClustering-based Token Merge(CTM) Block ( ) 人 心
ఏҊख๏1ɿCTM Blockʹ͓͚ΔΫϥελϦϯά Density peaks 用 ρi δi ρi = exp
− 1 k ∑ xj ∈KNN(xi ) ||xi − xj ||2 2 xi δi = { minj:ρj >ρi ||xi − xj || 2 if ∃j s.t. ρj > ρi maxj ||xi − xj || 2 otherwise 大 ρi ρj 大 ρi
ఏҊख๏1ɿCTM Blockʹ͓͚ΔΫϥελϦϯά 大 心 高 ρi × δi ρi ×
δi ρi = exp − 1 k ∑ xj ∈KNN(xi ) ||xi − xj ||2 2 xi δi = { minj:ρj >ρi ||xi − xj || 2 if ∃j s.t. ρj > ρi maxj ||xi − xj || 2 otherwise 大 ρi ρj 大 ρi
ఏҊख๏1ɿCTM Blockʹ͓͚Δಛྔͷ݁߹ yi = ∑ j∈Ci epjxj ∑ j∈Ci epj
pj Ci yi Query Attention Yongming Rao, Wenliang Zhao, Benlin Liu, Jiwen Lu, Jie Zhou, and Cho-Jui Hsieh. Dynamicvit: E ff i cient vision transformers with dynamic token sparsi fi cation. Adv. Neu- ral Inform. Process. Syst., 2 0 21 .
ఏҊख๏1ɿCTM BlockޙͷAttentionͷܭࢉ CTM 用 (Query) K,V 小 Spatial Reductio Attention(Q,
K, V) = softmax ( QKT dk + P ) V Attention P
ఏҊख๏2ɿMulti-stage Token Aggregation Head ViT 用
ఏҊख๏2ɿMulti-stage Token Aggregation Head Transformer 方 Stage 4 Stage 3
Stage 2 Stage 1
ఏҊख๏2ɿMulti-stage Token Aggregation Head Transformer 方 Upsample 行
ఏҊख๏·ͱΊ 1 2
࣮ݧ 人 3 D 3 D
࣮ݧ݁Ռɿ࢟ਪఆλεΫ 手 手
࣮ݧ݁Ռɿ࢟ਪఆλεΫ CTM,MTA Head 方
ͦΕҎ֎ͷλεΫ 手
࣮ݧɿੜ͞ΕͨτʔΫϯͷൺֱ 大 人 手
࣮ݧɿੜ͞ΕͨτʔΫϯͷൺֱ 手
·ͱΊͱײ 文 手 目 Human-centric