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
Food Image Object Detection and Classification
Search
Leszek Rybicki
February 16, 2017
Research
2
14k
Food Image Object Detection and Classification
Part 1: Detection
Leszek Rybicki
February 16, 2017
Tweet
Share
More Decks by Leszek Rybicki
See All by Leszek Rybicki
Let's talk about Fakes
lunardog
0
94
How to Patch Image Classifiers
lunardog
0
1.6k
Towards Realistic Predictors - EN
lunardog
0
1.5k
Towards Realistic Predictors
lunardog
1
1.9k
Deep Learning Hot Dog Detector
lunardog
0
220
Finding beans in burgers: paper reading notes
lunardog
0
1.2k
Kelner: Serve Your Models
lunardog
0
99
Image Analysis at Cookpad
lunardog
1
1.5k
Kelner: serve your models
lunardog
1
310
Other Decks in Research
See All in Research
第60回名古屋CV・PRMU勉強会:CVPR2024論文紹介(Vision Transformer)
waka_90b
1
150
Как стать 10x экспертом
ikurochkin
1
110
言語処理学会30周年記念事業留学支援交流会@YANS2024:「学生のための短期留学」
a1da4
1
190
第60回名古屋CV・PRML勉強会:CVPR2024論文紹介(AM-RADIO)
naok615
0
200
SSII2024 [TS2] 深層学習に潜むバイアス
ssii
PRO
0
590
Physics of Language Models: Part 3.1, Knowledge Storage and Extraction
sosk
1
800
Weekly AI Agents News! 7月号 プロダクト/ニュースのアーカイブ
masatoto
0
120
ヘルプデスクの事例で学ぶAIエージェント
masatoto
13
7k
Kaggle役立ちアイテム紹介(入門編)
k951286
13
4k
SSII2024 [OS3] 基盤モデル(オープニング)
ssii
PRO
0
320
SSII2024 [SS1] 拡散モデルの今 〜 2024年の研究動向 〜
ssii
PRO
2
2.1k
Weekly AI Agents News! 6月号 プロダクト/ニュースのアーカイブ
masatoto
0
120
Featured
See All Featured
Helping Users Find Their Own Way: Creating Modern Search Experiences
danielanewman
29
2.2k
Pencils Down: Stop Designing & Start Developing
hursman
119
11k
Music & Morning Musume
bryan
46
6k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
326
21k
Teambox: Starting and Learning
jrom
131
8.7k
In The Pink: A Labor of Love
frogandcode
139
22k
Java REST API Framework Comparison - PWX 2021
mraible
PRO
27
7.4k
Build your cross-platform service in a week with App Engine
jlugia
228
18k
Navigating Team Friction
lara
183
13k
Building Your Own Lightsaber
phodgson
101
6k
The Pragmatic Product Professional
lauravandoore
31
6.2k
Web development in the modern age
philhawksworth
205
10k
Transcript
Food Image Object Detection and Classification Challenges and Solutions
Part 1: Detection
自己紹介 • リビツキ レシェック • ポーランド出身 • 2016~ クックパッド • github:
lunardog
Warning! This presentation contains images that may cause severe drooling
and stomach grumbling. @cookpad
History 歴史
ImageNet KWWSLPDJHQHWRUJ
ImageNet Large Scale Visual Recognition Competition KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&
ILSVRC 2010 task Classification )RUHDFKLPDJHDOJRULWKPV ZLOOSURGXFHDOLVWRIDWPRVW REMHFWFDWHJRULHVLQWKH GHVFHQGLQJRUGHURI FRQILGHQFH KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&
ILSVRC 2011 tasks 1. Classification 2. *Classification with localization *tester
task
KWWSFVQVWDQIRUGHGXV\OODEXVKWPO Classification + Localization
ILSVRC 2012 tasks 1. Classification 2. Classification with localization 3.
Fine-grained classification
Fine-grained classification KWWSZZZLPDJHQHWRUJFKDOOHQJHV/695&
AlexNet ,PDJHQHWFODVVLILFDWLRQZLWKGHHSFRQYROXWLRQDOQHXUDOQHWZRUNV $.UL]KHYVN\,6XWVNHYHU*(+LQWRQ$GYDQFHVLQQHXUDOLQIRUPDWLRQ SURFHVVLQJV\VWHPV
ILSVRC 2013 tasks 1. Detection 2. Classification 3. Classification with
localization
ILSVRC 2014 tasks 1. Detection 2. Classification 3. Classification with
localization
Object Detection KWWSFVQVWDQIRUGHGXV\OODEXVKWPO
Deep Learning KWWSVGHYEORJVQYLGLDFRP
ILSVRC 2015 tasks 1. Object detection 2. Object localization 3.
*Object detection from video 4. *Scene classification
ILSVRC 2016 tasks 1. Object localization 2. Object detection 3.
Object detection from video 4. Scene classification 5. Scene parsing
Cookpad 2016
画像データセット 1997年~ レシピ数:国内約260万 + 国外 + つくれぽ + 手順写真 17言語、60カ国
※数字は2017年02月時点のものです
画像解析の研究関心 • これは料理ですか? • どの料理ですか? • 料理はどこですか? • 。。。 Part
2
Where is the food? 料理はどこですか?
ゴール )LQGIRRGLQWKHLPDJHGUDZ DERXQGLQJER[DURXQGWKH IRRGLWHPLQFOXGLQJWKH GLVKLIYLVLEOH
,IWKHUHDUHPXOWLSOHLWHPV GUDZDERXQGLQJER[ DURXQGHDFKRQH ゴール
ground truth bounding box > 0.9 We count it as
a positive detection if Intersection over Union ratio is greater than 0.9. ƴ
QXPEHURIWUXHSRVLWLYHV QXPEHURIJURXQGWUXWKER[HV ƴ ƴ ƴ QXPEHURIWUXHSRVLWLYHV QXPEHURIJHQHUDWHGER[HV 再現率 (precision) (recall)
ƴ ƴ
Methods
1. Build a classifier 2. Pick Regions of Interest 3.
Run classifier on each region 4. Remove duplicate detections IDEA
Fast, Faster R-CNN 5LFKIHDWXUHKLHUDUFKLHVIRUDFFXUDWHREMHFWGHWHFWLRQDQGVHPDQWLFVHJPHQWDWLRQ 5RVV*LUVKLFN-HII'RQDKXH7UHYRU'DUUHOO-LWHQGUD0DOLN )DVWHU5&117RZDUGV5HDO7LPH2EMHFW'HWHFWLRQZLWK5HJLRQ3URSRVDO1HWZRUNV 6KDRTLQJ5HQ.DLPLQJ+H5RVV*LUVKLFN-LDQ6XQ
)DVW5&11 5RVV*LUVKLFN
問題 1. Computational cost 2. Context is important 3. ...but
context can be confusing. KDQG IRRG JUDVV IRRG KWWSSL[DED\FRP
Single Shot Detector 66'6LQJOH6KRW0XOWL%R['HWHFWRU :HL/LX'UDJRPLU$QJXHORY'XPLWUX(UKDQ&KULVWLDQ6]HJHG\ 6FRWW5HHG&KHQJ<DQJ)X$OH[DQGHU&%HUJ
Either The Least Or Most Employable Person Ever 7KH+XIILQJWRQ3RVW JLWKXEFRPSMUHGGLH
SMUHGGLHFRPGDUNQHW ZZZNDJJOHFRPSMUHGGLH Joseph Redmon
You Only Look Once <RX2QO\/RRN2QFH8QLILHG 5HDO7LPH2EMHFW'HWHFWLRQ -RVHSK5HGPRQ6DQWRVK'LYYDOD5RVV *LUVKLFN$OL)DUKDGL 'HF
<2/2%HWWHU)DVWHU 6WURQJHU -RVHSK5HGPRQ$OL)DUKDGL
<RX2QO\/RRN2QFH8QLILHG5HDO7LPH2EMHFW'HWHFWLRQ -RVHSK5HGPRQ6DQWRVK'LYYDOD5RVV*LUVKLFN$OL)DUKDGL YOLO in Context
None