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
Paper-Survey: Objects as Points
Search
fam_taro
April 19, 2019
Science
0
2.3k
Paper-Survey: Objects as Points
fam_taro
April 19, 2019
Tweet
Share
More Decks by fam_taro
See All by fam_taro
NeRFの概要と 派生系についてのふんわり紹介
fam_taro
3
3.9k
実践 PyTorch Lightning (2019/11/30 分析コンペLT会 #1)
fam_taro
3
4.4k
Paper:ShapeMask
fam_taro
0
53
Summary: Objects as Points
fam_taro
0
3.1k
Tensorコアを使った PyTorch の高速化について
fam_taro
4
3.8k
Sequence to Sequence Learning with Neural Networks
fam_taro
1
1k
Other Decks in Science
See All in Science
Machine Learning for Materials (Lecture 8)
aronwalsh
0
410
インフラだけではない MLOps の話 @事例でわかるMLOps 機械学習の成果をスケールさせる処方箋 発売記念
icoxfog417
2
520
【人工衛星開発】能見研究室紹介動画
02hattori11sat03
0
140
Spectral Sparsification of Hypergraphs
tasusu
0
160
ECUACIÓN DE ESTADO DEL VIRIAL
borischicoma
0
160
教師なしテンソル分解に基づく、有糸分裂後の転写再活性化におけるヒストン修飾ブックマークとしての転写因子候補の抽出法
tagtag
0
110
ICRA2024 速報
rpc
3
5.1k
Pericarditis Comic
camkdraws
0
670
ultraArmをモニター提供してもらった話
miura55
0
180
Improving Search @scale with efficient query experimentation @BerlinBuzzwords 2024
searchhub
0
240
AI科学の何が“哲学”の問題になるのか ~問いマッピングの試み~
rmaruy
1
2.2k
Transformers are Universal in Context Learners
gpeyre
0
490
Featured
See All Featured
Why You Should Never Use an ORM
jnunemaker
PRO
53
9k
The Cost Of JavaScript in 2023
addyosmani
45
6.6k
Building Adaptive Systems
keathley
38
2.2k
実際に使うSQLの書き方 徹底解説 / pgcon21j-tutorial
soudai
167
49k
Testing 201, or: Great Expectations
jmmastey
38
7k
The Language of Interfaces
destraynor
154
24k
What’s in a name? Adding method to the madness
productmarketing
PRO
22
3.1k
Teambox: Starting and Learning
jrom
132
8.7k
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
31
2.7k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
47
5k
BBQ
matthewcrist
85
9.3k
Fantastic passwords and where to find them - at NoRuKo
philnash
50
2.8k
Transcript
จLT: Objects as Points h"ps:/ /arxiv.org/abs/1904.07850 2019/04/19 ౻ຊ༟հ 1
࣍ • ஶऀใ • ֓ཁ • ͜Ε·ͰͷϞσϧͱͷҧ͍ • ਫ਼ •
ͦͷଞײ 2
ஶऀใ • Xingyi Zhou(UT Aus1n) • Dequan Wang(UC Berkeley) •
Philipp Krähenbühl(UT Aus1n) 3
ಛ • ମݕग़Ϟσϧ • ༗໊ͳྫ: SSD, YOLOv3, Re.naNet, M2Det... •
ݕग़ͷΈͳΒͣ࢟ɾdepthɾ͖ɾ3d size ʹద༻͍ͯ͠Δ • backbone ͱͯ͠ DLA(deep layers aggrega.on) Hourglass(CornerNet Ͱ ༻) Λ༻ 4
ಛ • bounding box ΛΘͣʹݕग़Λߦ͏Ϟσϧ(keypointਪఆ) • bounding box ༻ͷ grid
ͷΘΓʹ͕ࡉ͔͍ heatmap(H, W Λ4Ͱׂͬͨఔ ͷͷ) Λग़ྗ • heatmap ͕ߴ͍ॴ() Λମͷத৺ͱਪఆ • த৺ͱͳΔॴͷ feature ͔Βମͷେ͖͞ɾࢄԽޡࠩΛਪఆ • ࢄԽޡࠩ = heatmap ʹͨ͠ࡍͷޡࠩ • େ͖͞ʹ͍ͭͯ scale ͍ͯ͠ͳ͍(ͦͷ··ͷ) 5
ಛ • ༧ଌϘοΫε = heatmap ͷ࠲ඪ + ༧ଌϘοΫεαΠζ + ༧ଌࢄԽޡࠩ
• ֶशʹ͏ heatmap ͷ 1ମʹ͖ͭ 1ͭͷΈ • SSD ͷΑ͏ʹ IoU ͷॏͳΓ۩߹Ͱ background ͔൱͔Λ͚ͳ͍ • ෳ box ग़͞ͳ͍͜ͱΛલఏͱ͍ͯ͠Δ • ಉ͡ΫϥεͰॏͳͬͯ͠·͏߹͕͋Δ͕શମͷ 0.1 % ະຬͰ RCNN(2% ະ ຬ) ΑΓখ͍͞ 6
Πϝʔδਤ 7
͜Ε·ͰͷϞσϧͱͷҧ͍ • Object detec*on with implicit anchors(SSD, YOLO, Re*naNet )ͱͷҧ͍
• CenterNetശͷॏͳΓͰͳ͘ҐஔͷΈʹج͍ͮͯʮΞϯΧʔʯΛׂ • લܠͱഎܠͷྨʹؔ͢Δखಈͷ͖͍͠ͳ͍(IoU 0.5 > ͱ͔) • ମຖʹϙδςΟϒͳΞϯΧʔ1͚ͭͩͳͷͰ NMS Λඞཁͱ͠ͳ͍ • We simply extract local peaks in the keypoint heatmap • keypoint heatmap ͔ΒϩʔΧϧϐʔΫΛநग़͢Δ͚ͩͰྑ͍ 8
͜Ε·ͰͷϞσϧͱͷҧ͍ • Object detec*on with implicit anchors(SSD, YOLO, Re*naNet )ͱͷҧ͍
• CenterNetΑΓେ͖ͳग़ྗղ૾Λ͏ • mask r-cnn ͱ͔ͱൺֱͯ͠ • output stride of 16 • ͜ΕʹΑΓෳͷΞϯΧʔ͕ෆཁͱͳΔʁʁʁʁ • [1711.08189] An Analysis of Scale Invariance in Object Detec*on - SNIP 9
͜Ε·ͰͷϞσϧͱͷҧ͍ • Object detec*on by keypoint es*ma*on(CornerNet, ExtremeNet )ͱͷҧ͍ •
্ه 2ͭ keypoint ݕग़ޙʹ Έ߹ΘͤΛ grouping ͢Δඞཁ͕͋Δ • ͘ͳͬͯ͠·͏ • CenterNet ඞཁͱ͠ͳ͍ • ͍ʂ 10
ਫ਼ 11
ਫ਼(M2Det ͷ݁ՌΛࢹͰՃͯ͠Έͨ) 12
ͦͷଞײ • Backbone ͱͯ͠ DLA Λ͑ΔͷΛॳΊͯͬͨ • Ή͠Ζ DLA ॳΊͯΓ·ͨ͠
! • NMS ͕ෆཁʹͳΔͷຯʹخ͍͠ • anchor ͕ফ͑Δͷخ͍͠ • খ͍͞ମʹରͯ͠ͲΕ͚ͩରԠͰ͖Δ͔֬ೝ͠ͳ͍ͱ 13