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
4.1k
実践 PyTorch Lightning (2019/11/30 分析コンペLT会 #1)
fam_taro
3
4.5k
Paper:ShapeMask
fam_taro
0
68
Summary: Objects as Points
fam_taro
0
3.2k
Tensorコアを使った PyTorch の高速化について
fam_taro
4
4k
Sequence to Sequence Learning with Neural Networks
fam_taro
1
1.1k
Other Decks in Science
See All in Science
データマイニング - ノードの中心性
trycycle
PRO
0
220
02_西村訓弘_プログラムディレクター_人口減少を機にひらく未来社会.pdf
sip3ristex
0
520
実力評価性能を考慮した弓道高校生全国大会の大会制度設計の提案 / (konakalab presentation at MSS 2025.03)
konakalab
2
180
データベース02: データベースの概念
trycycle
PRO
2
780
トラブルがあったコンペに学ぶデータ分析
tereka114
2
1.7k
深層学習を用いた根菜類の個数カウントによる収量推定法の開発
kentaitakura
0
170
機械学習 - 授業概要
trycycle
PRO
0
210
機械学習 - 決定木からはじめる機械学習
trycycle
PRO
0
1k
ガウス過程回帰とベイズ最適化
nearme_tech
PRO
1
470
Gemini Prompt Engineering: Practical Techniques for Tangible AI Outcomes
mfonobong
2
130
A Guide to Academic Writing Using Generative AI - A Workshop
ks91
PRO
0
120
04_石井クンツ昌子_お茶の水女子大学理事_副学長_D_I社会実現へ向けて.pdf
sip3ristex
0
530
Featured
See All Featured
Refactoring Trust on Your Teams (GOTO; Chicago 2020)
rmw
34
3.1k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
50k
Into the Great Unknown - MozCon
thekraken
40
1.9k
YesSQL, Process and Tooling at Scale
rocio
173
14k
A Tale of Four Properties
chriscoyier
160
23k
JavaScript: Past, Present, and Future - NDC Porto 2020
reverentgeek
50
5.5k
Faster Mobile Websites
deanohume
308
31k
No one is an island. Learnings from fostering a developers community.
thoeni
21
3.4k
Making Projects Easy
brettharned
116
6.3k
The Cult of Friendly URLs
andyhume
79
6.5k
Easily Structure & Communicate Ideas using Wireframe
afnizarnur
194
16k
Git: the NoSQL Database
bkeepers
PRO
431
65k
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