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
57
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
非同期コミュニケーションの構造 -チャットツールを用いた組織における情報の流れの設計について-
koisono
0
140
240510 COGNAC LabChat
kazh
0
130
はじめてのバックドア基準:あるいは、重回帰分析の偏回帰係数を因果効果の推定値として解釈してよいのか問題
takehikoihayashi
2
730
WeMeet Group - 採用資料
wemeet
0
3.2k
Boil Order
uni_of_nomi
0
120
プロダクト開発を通して学んだナレッジマネジメントの哲学
sonod
0
150
The Incredible Machine: Developer Productivity and the Impact of AI
tomzimmermann
0
390
Sociovirology
uni_of_nomi
0
100
MoveItを使った産業用ロボット向け動作作成方法の紹介 / Introduction to creating motion for industrial robots using MoveIt
ry0_ka
0
160
いまAI組織が求める企画開発エンジニアとは?
roadroller
2
1.3k
20分で分かる Human-in-the-Loop 機械学習におけるアノテーションとヒューマンコンピューターインタラクションの真髄
hurutoriya
5
2.3k
理論計算機科学における 数学の応用: 擬似ランダムネス
nobushimi
1
340
Featured
See All Featured
Practical Orchestrator
shlominoach
186
10k
Designing the Hi-DPI Web
ddemaree
280
34k
Designing Experiences People Love
moore
138
23k
The MySQL Ecosystem @ GitHub 2015
samlambert
250
12k
Practical Tips for Bootstrapping Information Extraction Pipelines
honnibal
PRO
10
720
Keith and Marios Guide to Fast Websites
keithpitt
409
22k
The Power of CSS Pseudo Elements
geoffreycrofte
73
5.3k
Designing for Performance
lara
604
68k
Git: the NoSQL Database
bkeepers
PRO
427
64k
VelocityConf: Rendering Performance Case Studies
addyosmani
325
24k
Measuring & Analyzing Core Web Vitals
bluesmoon
4
120
Six Lessons from altMBA
skipperchong
27
3.5k
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