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
20190223_nlpaperchallenge_CV_4.3to5.5
Search
yoppe
February 23, 2019
Science
2
760
20190223_nlpaperchallenge_CV_4.3to5.5
Presentation at
https://nlpaper-challenge.connpass.com/event/118557/
.
yoppe
February 23, 2019
Tweet
Share
More Decks by yoppe
See All by yoppe
20211023_recsys2021_paper_reading_YoheiKikuta
diracdiego
2
450
20201121_oldpaperreading_computing_machinery_and_intelligence
diracdiego
0
150
20200906_ACL2020_metric_for_ordinal_classification_YoheiKikuta
diracdiego
1
1.2k
20191102_ACL2019_adversarial_examples_in_NLP_YoheiKIKUTA
diracdiego
2
1.4k
20180701_CVPR2018_reading_YoheiKIKUTA
diracdiego
3
1.1k
20180414_WSDM2018_reading_YoheiKIKUTA
diracdiego
0
690
20180306_NIPS2017_DeepLearning
diracdiego
4
5.8k
20180215_MLKitchen7_YoheiKIKUTA
diracdiego
0
380
20180210_Cookpad_TechConf2018_YoheiKIKUTA
diracdiego
5
1.1k
Other Decks in Science
See All in Science
証明支援系LEANに入門しよう
unaoya
0
320
Презентация программы магистратуры СПбГУ "Искусственный интеллект и наука о данных"
dscs
0
370
第61回コンピュータビジョン勉強会「BioCLIP: A Vision Foundation Model for the Tree of Life」
x_ttyszk
1
1.5k
拡散モデルの原理紹介
brainpadpr
3
4.6k
Machine Learning for Materials (Lecture 3)
aronwalsh
0
990
Machine Learning for Materials (Lecture 6)
aronwalsh
0
500
ECUACIÓN DE ESTADO DEL VIRIAL
borischicoma
0
160
Raccoon Roundworm
uni_of_nomi
0
160
様々な侵入者タイプに対応した適切な警備計画の策定 / Patrol route design considering various types of intrudes
konakalab
0
170
20240127_OpenRadiossエアバッグ解析
kamakiri1225
0
260
はじめての「相関と因果とエビデンス」入門:“動機づけられた推論” に抗うために
takehikoihayashi
17
6.8k
機械学習を支える連続最適化
nearme_tech
PRO
1
120
Featured
See All Featured
ピンチをチャンスに:未来をつくるプロダクトロードマップ #pmconf2020
aki_iinuma
107
49k
I Don’t Have Time: Getting Over the Fear to Launch Your Podcast
jcasabona
27
1.9k
GraphQLの誤解/rethinking-graphql
sonatard
66
9.9k
Making the Leap to Tech Lead
cromwellryan
132
8.9k
Scaling GitHub
holman
458
140k
The Illustrated Children's Guide to Kubernetes
chrisshort
48
48k
Testing 201, or: Great Expectations
jmmastey
38
7k
Building Better People: How to give real-time feedback that sticks.
wjessup
363
19k
Gamification - CAS2011
davidbonilla
80
5k
Distributed Sagas: A Protocol for Coordinating Microservices
caitiem20
328
21k
A better future with KSS
kneath
238
17k
The Pragmatic Product Professional
lauravandoore
31
6.3k
Transcript
ୈ2ճ nlpaper.challenge NLP/CV ަྲྀษڧձ ը૾ೝࣝ ୈ4.3ষ~ୈ5.5ষ 20190223 Yohei KIKUTA
ࣗݾհ • Twitter ID @yohei_kikuta • Resume • ࠷ۙୀ৬ͯ͠ແ৬ʹͳΓ·ͨ͠ ϒϩάΤϯτϦ
ແ৬ͱͯ͠Έ͍ͨਓ͓͕͚͍ͩ͘͞ʂ ΫοΫύουྑ͍ձࣾͳͷͰస৬͍ͨ͠ਓͥͻͲ͏ͧʂ
ଟ༷ମֶश͚ͩৄ͘͠Γ·͢ • ը૾ೝࣝ ຊͷ 4.3~5.5 Λൃද • ہॴಛʹ͔ؔͯ͠ͳΓߴີͰ࣌ؒʹ͖͠Εͳ͍ ଟ༷ମֶश ΧʔωϧؔۙࣅʢಛʹͦͷͨΊͷجૅ͕ࣝॏ͍ʣ
ͦͷ΄͔༷ʑͳ • શମͷ·ͱΊͱུ֓Λہॴಛͷ෦Λܰ͘આ໌ͨ͠ޙɺଟ ༷ମֶशΛৄ͘͠આ໌ Q. ͳͥଟ༷ମֶशͳͷ͔ʁ A. ͕ࣗগ͠ਅ໘ʹษڧͯ͠Έ͔͔ͨͬͨΒ
4.3~4.6 ͷ·ͱΊ ہॴಛͰࣦΘΕۭͨؒใΛ༩ͨ͠Γ͢Δʢ4.6ʣ
5.1~5.5 ͷ·ͱΊ ʢ֬తʣޯ߱Լ๏χϡʔτϯ๏Ͱύϥϝλ w Λֶश
ہॴಛΛ༻͍ͨ࠶ߏங ͜Ε݁ہͲͷล͕ଟ༷ମͳͷ͔ʁ ͱ͍͏͕ฉ͖͑ͯͦ͜͏͕ͩɺͦΕޙͰগ͠ৄ͘͠આ໌
ಛࣸ૾ʹΑΔΧʔωϧͷۙࣅ ػցֶशʹଌ͍Δͷʁͱ͍͏ٙΛ࣋ͭਓ Mercer’s theorem ͱ͔ Bochner’s theorem ͱ͔Λݟ·͠ΐ͏
ۭؒใͷ׆༻ • ϓʔϦϯάʹΑࣦͬͯΘΕΔҐஔใΛखͰՃ͑Δ • ہॴهड़ࢠͷҐஔεέʔϧΛՃ͑Δ • ہॴهड़ࢠͷࣗݾ૬ؔߦྻͷཁૉΛՃ͑Δ • spatial pyramid
ϓʔϦϯάޙͷಛʹۭؒใΛ༩
ଟ༷ମֶश ଟ༷ମֶशʹͯ͠গ͠ৄ͘͠આ໌͢Δʢݸਓతڵຯʣ આ໌͢ΔͷҎԼͷτϐοΫɿ • ͦͦଟ༷ମͱʁʢֶతʹݫີͳ͠ͳ͍ʣ • ଟ༷ମֶशʹࢸΔϞνϕʔγϣϯ • Ұͭͷྫͱͯ͠ہॴ࠲ඪ coding
ͷվળͷจΛհ [140] K. Yu, T. Zhang. Improved local coordinate coding using local tangents. In ICML, 2010.
ଟ༷ମͱʁ ہॴతʹ Euclid ۭؒͰهड़Ͱ͖ΔਤΛషΓ߹ΘͤͯදͤΔ ྫʣද໘Λߟ͑Δ ※ Φ ͱ Θ ͚ͩͰ࠲ඪܥషΓ͖Εͳ͍ʢશͳٿͰͳ͍ʣ
ہॴతʢզʑͷৗεέʔϧʣʹ Euclid ࠲ඪͰهड़Ͱ͖Δ ͦͷ࠲ඪΛషΓ߹ΘͤΕද໘શମΛΧόʔͰ͖Δ ͦͷΑ͏ͳషΓ߹ΘͤͷใͰ 3 ࣍ݩͷٿͷใٞՄ
ଟ༷ମͱʁ σʔλͷॅΉۭؒಉ͡Α͏ͳͷͩͱ૾͞ΕΔ ͜ͷΑ͏ͳঢ়گͰɺྫ͑ೋؒͷڑΛଌΔͱ͖ʹߴ࣍ݩۭ ؒͰͷ Euclid ڑෆద͔͠Εͳ͍ → ଟ༷ମʹԊͬͯڑΛଌΔํ͕ੑ࣭Λଊ͑ΒΕͦ͏ʢଌઢʣ → ใزԿʹ͓͚Δࣗવޯ๏ͳͲ͜ΕΛ͍ͬͯΔ
ଟ༷ମֶशʹࢸΔಈػ • ࣍ݩͷढ͍ͷճආ ྫʣσʔλେྔʹ͋Ε kNN Ͱ͍͍͡ΌΜ → μϝͰ͢ • σʔλͷ༗͢ΔಛΛΑΓྑ͘Ѳ
ઌ΄ͲͷྫͷΑ͏ʹ୯ͳΔ Euclid ڑ͕ෆద͔͠Εͳ͍ ྫʣࣗવޯ๏ɺt-SNE • ༷ʑͳΞϓϩʔν͔Β৽ͨͳݟ͕ಘΒΕΔ͔ ඍزԿతͳΞϓϩʔνʢہॴతʣˠ େମͷͬͪ͜ Ґ૬زԿతͳΞϓϩʔνʢେҬతʣˠ ࠓ৮Εͳ͍
ʢิʣ࣍ݩͷढ͍ • ಛྔͷ࣍ݩ͕େ͖͗͢Δ߹ Ϟσϧ͕ෳࡶ͗ͯ͢దʹֶशͰ͖ͳ͍ • σʔλۭؒͷ࣍ݩ͕େ͖͗͢Δ߹ ྫͱͯ͠ΫϥελϦϯάΛߟ͑Δ ٿ໘ूதݱʹΑΓɺҟͳΔؒͷڑ͕͘͠ͳ͍ͬͯ͘ ݁Ռͱͯ͠ A
͔Βݟͯ B C ΄΅ಉ͡Ͱ۠ผෆՄ ʢ࣍ݩͷढ͍ͷ ͡Ίͯͷύλʔϯೝࣝ ͕ৄ͍͠ʣ
ଟ༷ମֶशͷྫ ہॴ࠲ඪ coding Λվળ͢Δ͜ͱΛߟ͑Δ K. Yu, T. Zhang. Improved local
coordinate coding using local tangents. In ICML, 2010. ࠷ऴతͳඪσʔλ͕͢ଟ༷ମͷࡏతͳ࣍ݩʢPCA Ͱٻ ΊΔʣΛߟྀ͠ɺͦͷใΛͬͯ coding Λิਖ਼
४උ
ہॴ࠲ඪ coding ʹΑΔۙࣅ
(4.79) ࣜͷূ໌
ہॴ࠲ඪ coding ͷֶश๏
֦ுہॴ࠲ඪ coding
σʔλଟ༷ମͷఆٛ
ہॴಛ coding with u ূ໌ུʢઌ΄Ͳͷূ໌͕͔ͬͯΕ͘͠ͳ͍ʣ u (local) PCA ͳͲͰٻΊɺm
खͰܾΊΔύϥϝλ c(M) ؔʹ͓͚ΔϦϓγοπఆʹ૬ ॏཁͳͷ c(M) ͕খ͍͞߹ʹ bound ͕Ωπ͘ͳΔͱ͍͏͜ͱ → ͜Εখ͞ͳྖҬͰσʔλଟ༷ମ͕ flat ͳߏͰ͋Δ߹ → “ఆੑత” ͳԾఆͰ flat Ͱͳͯ͘༗ޮͳ߹͋ΓಘΔ
ֶशΞϧΰϦζϜ จͷΞϧΰϦζϜࡌͤΔʢs, m hyperparameterʣ
࣮ݧ݁ՌɿMNIST Cross validation ʹΑΓ s = 0, m = 64
୯७ͳہॴಛ coding ͱൺΔͱ anchor ͕গͳͯ͘ྑ͍
࣮ݧ݁ՌɿCIFAR10 Cross validation ʹΑΓ s = 10, m = 256
ͪ͜Β anchor ͕গͳͯ͘ྑ͍݁ՌΛ͍ࣔͯ͠Δ
ଟ༷ମֶशʹཱͭ • σʔλͷߏΛ͏·͘ଊ͑ͯ༗༻ͳಛྔΛ࡞Εͨ • ہॴੑʹΛ͠ͳ͕Βߴ࣍ݩใΛ࣍ݩͰۙࣅ • ࣮ࡍʹࣝผੑೳ্͕ • σΟʔϓϥʔχϯάͰଟ༷ମֶशڵຯਂ͍τϐοΫ ใزԿ
ϦʔϚϯଟ༷ମ্ͰֶशΛఆࣜԽ …
4.3~4.6 ͷ·ͱΊʢ࠶ܝʣ ہॴಛͰࣦΘΕۭͨؒใΛ༩ͨ͠Γ͢Δʢ4.6ʣ