SlideShare a Scribd company logo
CC6 C 2B6 2 C D6 6 6 C 6A2C B A 2 6
.6BC A2C C96 -A6B6 6 0 3 6 BC AC B
I
1-.
•
• ) [ V
• A O LIR +1 ]LIDB E LC
• ( A O B E LC
• = +
. G M
8 7 )9
P . G M
81 2 (9
P .
80 , 9
@
- - - - - - -
- - - - - -
• , 3 3
•
A
Input
Ours
Ground
truth
Mix Raindrop Blur Noise JPEG
SE R T UA PXC I MKLNE O
-
•
• 4
- -
- -
D
• B
• 5
•
+
,,K QHN
• . 6
•
VRP ILM
2 0
2 0 + C 2 C 0
, 219 8
C C
NO P
, ILE A K D I EI DI E
I ED E C IE I ED
• D DE 0 D C D 0 D 1 A M A A I D
• 1E EA 2D K IM ,
• 9 E A 7
• 5
2 8 810 1 , 1
2 8 810 881 82 1 , 1
9:
I
(
op1
op2
op3
op4
op1
op2
op3
op4
…
Input
op1
op2
op3
op4
)1 2
D A F
• 3 03
• 3
• 0
3 1 3 1
-
• 2 ( ) 6
• 2 ( ) 12 3×3
• 3 - )2 3×3
• ( 1 ) (
-
FeatureExtraction
Block
Operation-wise
AttentionLayer
Operation-wise
AttentionLayer
Reconstruction
Layer
Operation-wise
AttentionLayer
•
• 1
1
3
3
AC
+ 4 18C 7E 8 8 F 8
CC 01
. ,E 2AE88H8 7 8 F C 01
! ∈ ℝ$
• 5%&'( ∈ ℝ)×+×$ - ! ∈ ℝ$
• 1
!" = [%&"
'
, … , %&"
*
]
•
,- ∈ ℝ0×2, ,3 ∈ ℝ|*|×05" 6" = ,78(,'6")
%&"
;
=
exp(5"(6"))
∑ exp(5"(6"))
=
exp(&"
;
)
∑;@'
|*|
exp(&"
;
)
→ B C 6 1
! "#
• $%&'(')*% +,-. 1×1
• $%&'(')*% +,-. 3×3
• $%&'(')*% +,-. 5×5
• $%&'(')*% +,-. 7×7
• $%&'(')*% 45*'6%4 +,-. 3×3 (( = 2)
• $%&'(')*% 45*'6%4 +,-. 5×5 (( = 2)
• $%&'(')*% 45*'6%4 +,-. 7×7 (( = 2)
• '.%(';% &,,*5-; 3×3
!" #"
$×$
. 1×1
ℱ(: 1×1 *+,-
• - = 1
• 4 9 =
• =
Feature maps
!×#×$
%&'(
)&
*+,-(
Feature maps
!×#×$
%&
Feature maps
!×#×$
%&-,'(
…
OperationLayerAttentionLayer
…
Concat
1×1conv.
/&
OperationLayer
Concat
1×1conv.
*+,-,
• - -- - 2 0 -
Feature maps
!×#×$
%&'(
)&
*+,-(
Feature maps
!×#×$
%&
Feature maps
!×#×$
%&-,'(
…
OperationLayerAttentionLayer
…
Concat
1×1conv.
/&
OperationLayer
Concat
1×1conv.
*+,-,
• 2
• 1 3 1 23 1 3 ,
• 2 +
• 1 3 1 23 1 3 ,
• 2
• 1 1 1 3 1 23 1 3 , 3 312
,
• D : 8 : :
• 63×63 C I: PYV R[V K V ]
• : + C 8 : : : + C 8 :
• 2 b
• a 4 5 9 ]
,
, :
- :9
4 5 3 , 8 : : 9::C : 8: : : . ,201
02.1 22 D IK
16 8 76 3 , 54 4 6
EP PE 6I D 6MDE E :ESE E
6E IC 8:79 ::36 8:79 ::36 8:79 ::36
1L077 ) ) ) ) ) )- (
95 9EP M E , ( () )) ) )- )
4 L E ETMLD RPPI L DELMIPE . 9EPIDR E LIL M DEEN CLL M IK E DELMIPIL 3222 LP C IMLP ML 3K E 8 MCEPPIL . ( ))
4 R E 0 IL MM C IL M IK E EP M IML BT DEEN EIL M CEKEL E LIL 3L 0 89 ,
• v tnr 077edf
• v uo 8 E ILED 077cighm]aYZp VZs bl [
u DIP M IML l
1 4
- 4 2-
2 42 4
PS IG 5 CD 5D R G PSV
JL O
• 1(3)( 0) 5
• 33 A D 5
• ,5ECC 5 C ,5ECC 5 E 1 , 7 A CC 5 D 57DC
( CD D C 2 CD
0E D 7D
] V [cedf kgn 73 7 LMIK ob a
• h mi P I K LMIK M I Yl aYR
182785 6 1 76 .41 01 1 376
/6 KI K I M IMM L K
(. ) ) ) , . ( ( ( . )-
,) . ,- % % , .
% ) ), - %
(, (. - ( , ( . , ) ( )
,( ) ,( - ) ) , , . (
% % %
M C K IP M I CIKL KLI M LC LIA MK MO
(( , . ) ( )( . ) )) - ( () ) -
- ( ) , ,- - - ( % . , , -
% - , % ) - %
) - ( (. ( ( ) , )) , () , )( ) ( (( - ). -
. - ) - - - . . , , ( , . ( ) ( ( , .
% % %
850
,
89
73 7 LMIK
P I K LMIK M I
89
73 7 LMIK
P I K LMIK M I
4 MCI
2 9 M 0K AM MII C AIK K LMIK M I K AIK M K 1 0867 -
Cat
Cat
Cat
Sheep
Person
Person
Person
Person
Boat
Dog
Dog
Person
Cow
Cow
Dog
Dog
Dog
Dog
Person
Person
Person
Person
Person
Dog
Bottle
Bottle
Clean
Distorted
RL-Restore [1]
Ours
Cat
Person
Person
Person
Person
Person
Person
Person
Person
Cat
TVmonitor
Person
Person
Person
Person
Horse
Horse Horse
HorseCar
I JE A G
• .2 2 2A5 0 1 IRQ
• 128×128 5 I
• 2 A5 2 385A 5A A5 2 385A
• ( , ) I P
)
0 1 . 2 5 2 5 C5 5 5 2 C5 2 C5 A2 2 5 D : 2 5 C2 2 A 5 2 5 ,.
52 A 5
• S - . 2
/
• - . 2 >9 - - 9 D
• - - - -
• a - G
A
Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions [CVPR 2019 読み会]
• RE N g
Ga e i J
• 1 h RE
N
• 33 3
33 3 P d J
1 E B P
G
: 9 58
2 199A () (- . -.
4429 TA) () . .(
3 103A ( - .(+
9
(
4 351 04 89 48
: 9 58
2 199A ( ) -- ,
8 N9 TA+ ( - -,-
9
. 4. 84 1 9168 .5 .9 42. 9168 .5
SK IM FKSTPRTKP h] bifkald [c eg
A) 6 C I 4 F T P CRF C CST C F M KDM SPM TKP PR E DCS F KNCI F PKSK I 5333 RC SCETKP S P 5NCI :RPE SSK I , . )+ -Z)+ -
A 8 IC NC 3 MPKTK I T PT TKCM P STC FCRF EP VPM TKP CM C TP EPF RS PR KNCI R STPRCTKP DY VPM TKP CRY S CRE 5 5187 -
A+ CK 8 N T 0 RSKST T N NPRY T PRL PR KNCI R STPRCTKP 5 511 ,
• 2CC C a
• t gec gecVy ] R
• C V s
• kbfapKy 0 1 Y I- V r R
• u 2CC C a R - 2 3 Y]K
ldm n hio c P [ VN L[
0 1 C 2 2 C 8 2 C 2 28 C 2C 3 C 2 8 .,-
•
• - -
• e r p
• D V I
• - 43 l I n
• - d 4 - ? e o m
•
• b g h d 4 a - -
i
• - -

More Related Content

PDF
20190225 DIY伝送装置
PDF
第三回勉強会 Keras担当回
PDF
複数スタイルの融合と 部分的適用を可能とする Multi-style Feed-forward Networkの提案
PDF
2019-02-09 ABCD浜松 「クロスプラットフォーム開発を検討しよう Xamarin編」
DOCX
แผนการจัดการเรียนรู้ที่ 1 เรื่อง การเขียนและการอ่านตัวเลขฮินดูอารบิก ตัวเลขไ...
PDF
MobileAct Nagoya #15 Cross-platform software
PDF
re:Invent 2018 recap for Gaming ~ゲーム関連セッションのご紹介~
PDF
第5回NIPS読み会・関西発表資料
20190225 DIY伝送装置
第三回勉強会 Keras担当回
複数スタイルの融合と 部分的適用を可能とする Multi-style Feed-forward Networkの提案
2019-02-09 ABCD浜松 「クロスプラットフォーム開発を検討しよう Xamarin編」
แผนการจัดการเรียนรู้ที่ 1 เรื่อง การเขียนและการอ่านตัวเลขฮินดูอารบิก ตัวเลขไ...
MobileAct Nagoya #15 Cross-platform software
re:Invent 2018 recap for Gaming ~ゲーム関連セッションのご紹介~
第5回NIPS読み会・関西発表資料

What's hot (20)

PDF
Математическая модель системы оценки эффективности реализации программ развит...
PDF
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
PDF
Arran Map
PDF
中学生を対象とした 「数学と人間の活動」の授業開発 ー「石取りゲーム」を教材としてー
PDF
Spectrum sensing based on goodness of fit test with unilateral alternative hy...
PDF
異常検知とGAN: Efficient GAN
PDF
Encrypting sensitive data for puppet
PDF
[DL Hacks]Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternati...
DOCX
ใบงานที่ 4
PDF
Stalin and soviet industrialisation vox, cepr policy portal
PDF
Determinacion minimos cuadrados
PDF
창의력 향상을 위한 마인드맵 활용하기
PDF
PDF
[DL Hacks]Pruning Convolutional Neural Networks for Resource Efficient Inference
PDF
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
PDF
Ejercicio 8
PDF
залікове інтеграли
DOCX
Noveno1 p hugo
PDF
アーリース情報技術株式会社 会社案内 (2019/02/13)
PDF
eGovinnovation - Elenea Mugellini
Математическая модель системы оценки эффективности реализации программ развит...
【修士論文紹介】ソーシャルメディアからの作用を考慮した金融市場の観測・予測モデルの提案
Arran Map
中学生を対象とした 「数学と人間の活動」の授業開発 ー「石取りゲーム」を教材としてー
Spectrum sensing based on goodness of fit test with unilateral alternative hy...
異常検知とGAN: Efficient GAN
Encrypting sensitive data for puppet
[DL Hacks]Deep Neuroevolution: Genetic Algorithms Are a Competitive Alternati...
ใบงานที่ 4
Stalin and soviet industrialisation vox, cepr policy portal
Determinacion minimos cuadrados
창의력 향상을 위한 마인드맵 활용하기
[DL Hacks]Pruning Convolutional Neural Networks for Resource Efficient Inference
Spark MLlib ML Pipelines の概要 及びpysparkからの扱い方
Ejercicio 8
залікове інтеграли
Noveno1 p hugo
アーリース情報技術株式会社 会社案内 (2019/02/13)
eGovinnovation - Elenea Mugellini

Similar to Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions [CVPR 2019 読み会] (20)

PDF
katagaitai CTF workshop #10 AESに対する相関電力解析
PDF
技術とデザインの最適な関係; 技術の意味を与えるデザイン
PDF
Functional Gradient Boosting based on Residual Network Perception
PDF
A research paper introduction of Universal transformers
PDF
Prelude to halide_public
PDF
Distributed Denial of Service Attack Prevention at Source Machines
PDF
【CVPR 2019】Learning Cross Modal Embeddings with Adversarial Networks for Cook...
PDF
Наибольшая общая мера: 2500 лет
PDF
JTF2018_B30_k8s_operator_nobusue
PDF
vcdで日本語(3) long format が旧世界とのGateway
PDF
【ECCV 2018】CornerNet: Detecting Objects as Paired Keypoints
PDF
Cameroun - Repertoire des projets prioritaires à besoins de financement
PDF
kintone on EKS ― EKS で実現するインフラ自動構築パイプライン
PDF
第2回 基本演算,データ型の基礎,ベクトルの操作方法
PDF
Mat fin
PDF
إجراءات قائمة الشحن
PDF
音響信号に対する異常音検知技術と応用
PDF
الإستاتيكا
PDF
機械学習と自動微分
PDF
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...
katagaitai CTF workshop #10 AESに対する相関電力解析
技術とデザインの最適な関係; 技術の意味を与えるデザイン
Functional Gradient Boosting based on Residual Network Perception
A research paper introduction of Universal transformers
Prelude to halide_public
Distributed Denial of Service Attack Prevention at Source Machines
【CVPR 2019】Learning Cross Modal Embeddings with Adversarial Networks for Cook...
Наибольшая общая мера: 2500 лет
JTF2018_B30_k8s_operator_nobusue
vcdで日本語(3) long format が旧世界とのGateway
【ECCV 2018】CornerNet: Detecting Objects as Paired Keypoints
Cameroun - Repertoire des projets prioritaires à besoins de financement
kintone on EKS ― EKS で実現するインフラ自動構築パイプライン
第2回 基本演算,データ型の基礎,ベクトルの操作方法
Mat fin
إجراءات قائمة الشحن
音響信号に対する異常音検知技術と応用
الإستاتيكا
機械学習と自動微分
Theory and Methods for Unsupervised Anomaly Detection in Sounds Based on Deep...

More from MasanoriSuganuma (7)

PDF
0から理解するニューラルネットアーキテクチャサーチ(NAS)
PDF
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
PDF
高1から始める人工知能(AI)
PDF
When NAS Meets Robustness: In Search of Robust Architectures against Adversar...
PDF
When NAS Meets Robustness: In Search of Robust Architectures against Adversar...
PPTX
CNNの構造最適化手法について
PPTX
CNNの構造最適化手法(第3回3D勉強会)
0から理解するニューラルネットアーキテクチャサーチ(NAS)
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
高1から始める人工知能(AI)
When NAS Meets Robustness: In Search of Robust Architectures against Adversar...
When NAS Meets Robustness: In Search of Robust Architectures against Adversar...
CNNの構造最適化手法について
CNNの構造最適化手法(第3回3D勉強会)

Recently uploaded (20)

PPTX
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
DOCX
The AUB Centre for AI in Media Proposal.docx
PDF
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
PDF
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
PDF
Building Integrated photovoltaic BIPV_UPV.pdf
PPTX
sap open course for s4hana steps from ECC to s4
PPTX
Cloud computing and distributed systems.
PDF
cuic standard and advanced reporting.pdf
PPTX
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
PDF
Blue Purple Modern Animated Computer Science Presentation.pdf.pdf
PDF
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
PDF
MIND Revenue Release Quarter 2 2025 Press Release
PPTX
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
PDF
Encapsulation theory and applications.pdf
PPTX
Digital-Transformation-Roadmap-for-Companies.pptx
PPTX
Programs and apps: productivity, graphics, security and other tools
PPTX
Understanding_Digital_Forensics_Presentation.pptx
PDF
Dropbox Q2 2025 Financial Results & Investor Presentation
PPTX
Effective Security Operations Center (SOC) A Modern, Strategic, and Threat-In...
PPT
“AI and Expert System Decision Support & Business Intelligence Systems”
Detection-First SIEM: Rule Types, Dashboards, and Threat-Informed Strategy
The AUB Centre for AI in Media Proposal.docx
Build a system with the filesystem maintained by OSTree @ COSCUP 2025
Peak of Data & AI Encore- AI for Metadata and Smarter Workflows
Building Integrated photovoltaic BIPV_UPV.pdf
sap open course for s4hana steps from ECC to s4
Cloud computing and distributed systems.
cuic standard and advanced reporting.pdf
VMware vSphere Foundation How to Sell Presentation-Ver1.4-2-14-2024.pptx
Blue Purple Modern Animated Computer Science Presentation.pdf.pdf
Optimiser vos workloads AI/ML sur Amazon EC2 et AWS Graviton
MIND Revenue Release Quarter 2 2025 Press Release
KOM of Painting work and Equipment Insulation REV00 update 25-dec.pptx
Encapsulation theory and applications.pdf
Digital-Transformation-Roadmap-for-Companies.pptx
Programs and apps: productivity, graphics, security and other tools
Understanding_Digital_Forensics_Presentation.pptx
Dropbox Q2 2025 Financial Results & Investor Presentation
Effective Security Operations Center (SOC) A Modern, Strategic, and Threat-In...
“AI and Expert System Decision Support & Business Intelligence Systems”

Attention-Based Adaptive Selection of Operations for Image Restoration in the Presence of Unknown Combined Distortions [CVPR 2019 読み会]

  • 1. CC6 C 2B6 2 C D6 6 6 C 6A2C B A 2 6 .6BC A2C C96 -A6B6 6 0 3 6 BC AC B I 1-.
  • 2. • • ) [ V • A O LIR +1 ]LIDB E LC • ( A O B E LC • = + . G M 8 7 )9 P . G M 81 2 (9 P . 80 , 9 @
  • 3. - - - - - - - - - - - - - • , 3 3 • A Input Ours Ground truth Mix Raindrop Blur Noise JPEG SE R T UA PXC I MKLNE O
  • 6. ,,K QHN • . 6 • VRP ILM 2 0 2 0 + C 2 C 0 , 219 8
  • 7. C C NO P , ILE A K D I EI DI E I ED E C IE I ED • D DE 0 D C D 0 D 1 A M A A I D • 1E EA 2D K IM , • 9 E A 7 • 5
  • 8. 2 8 810 1 , 1 2 8 810 881 82 1 , 1
  • 10. D A F • 3 03 • 3 • 0 3 1 3 1 -
  • 11. • 2 ( ) 6 • 2 ( ) 12 3×3
  • 12. • 3 - )2 3×3 • ( 1 ) (
  • 14. AC + 4 18C 7E 8 8 F 8 CC 01 . ,E 2AE88H8 7 8 F C 01
  • 15. ! ∈ ℝ$ • 5%&'( ∈ ℝ)×+×$ - ! ∈ ℝ$ • 1
  • 16. !" = [%&" ' , … , %&" * ] • ,- ∈ ℝ0×2, ,3 ∈ ℝ|*|×05" 6" = ,78(,'6") %&" ; = exp(5"(6")) ∑ exp(5"(6")) = exp(&" ; ) ∑;@' |*| exp(&" ; ) → B C 6 1
  • 17. ! "# • $%&'(')*% +,-. 1×1 • $%&'(')*% +,-. 3×3 • $%&'(')*% +,-. 5×5 • $%&'(')*% +,-. 7×7 • $%&'(')*% 45*'6%4 +,-. 3×3 (( = 2) • $%&'(')*% 45*'6%4 +,-. 5×5 (( = 2) • $%&'(')*% 45*'6%4 +,-. 7×7 (( = 2) • '.%(';% &,,*5-; 3×3
  • 19. • - = 1 • 4 9 = • = Feature maps !×#×$ %&'( )& *+,-( Feature maps !×#×$ %& Feature maps !×#×$ %&-,'( … OperationLayerAttentionLayer … Concat 1×1conv. /& OperationLayer Concat 1×1conv. *+,-,
  • 20. • - -- - 2 0 - Feature maps !×#×$ %&'( )& *+,-( Feature maps !×#×$ %& Feature maps !×#×$ %&-,'( … OperationLayerAttentionLayer … Concat 1×1conv. /& OperationLayer Concat 1×1conv. *+,-,
  • 21. • 2 • 1 3 1 23 1 3 , • 2 + • 1 3 1 23 1 3 , • 2 • 1 1 1 3 1 23 1 3 , 3 312
  • 22. , • D : 8 : : • 63×63 C I: PYV R[V K V ] • : + C 8 : : : + C 8 : • 2 b • a 4 5 9 ] , , : - :9 4 5 3 , 8 : : 9::C : 8: : : . ,201
  • 23. 02.1 22 D IK 16 8 76 3 , 54 4 6 EP PE 6I D 6MDE E :ESE E 6E IC 8:79 ::36 8:79 ::36 8:79 ::36 1L077 ) ) ) ) ) )- ( 95 9EP M E , ( () )) ) )- ) 4 L E ETMLD RPPI L DELMIPE . 9EPIDR E LIL M DEEN CLL M IK E DELMIPIL 3222 LP C IMLP ML 3K E 8 MCEPPIL . ( )) 4 R E 0 IL MM C IL M IK E EP M IML BT DEEN EIL M CEKEL E LIL 3L 0 89 , • v tnr 077edf • v uo 8 E ILED 077cighm]aYZp VZs bl [ u DIP M IML l
  • 24. 1 4 - 4 2- 2 42 4
  • 25. PS IG 5 CD 5D R G PSV JL O • 1(3)( 0) 5 • 33 A D 5 • ,5ECC 5 C ,5ECC 5 E 1 , 7 A CC 5 D 57DC ( CD D C 2 CD 0E D 7D
  • 26. ] V [cedf kgn 73 7 LMIK ob a • h mi P I K LMIK M I Yl aYR 182785 6 1 76 .41 01 1 376 /6 KI K I M IMM L K (. ) ) ) , . ( ( ( . )- ,) . ,- % % , . % ) ), - % (, (. - ( , ( . , ) ( ) ,( ) ,( - ) ) , , . ( % % % M C K IP M I CIKL KLI M LC LIA MK MO (( , . ) ( )( . ) )) - ( () ) - - ( ) , ,- - - ( % . , , - % - , % ) - % ) - ( (. ( ( ) , )) , () , )( ) ( (( - ). - . - ) - - - . . , , ( , . ( ) ( ( , . % % % 850 , 89 73 7 LMIK P I K LMIK M I 89 73 7 LMIK P I K LMIK M I 4 MCI 2 9 M 0K AM MII C AIK K LMIK M I K AIK M K 1 0867 -
  • 28. I JE A G • .2 2 2A5 0 1 IRQ • 128×128 5 I • 2 A5 2 385A 5A A5 2 385A • ( , ) I P ) 0 1 . 2 5 2 5 C5 5 5 2 C5 2 C5 A2 2 5 D : 2 5 C2 2 A 5 2 5 ,. 52 A 5
  • 29. • S - . 2 / • - . 2 >9 - - 9 D • - - - - • a - G A
  • 31. • RE N g Ga e i J • 1 h RE N • 33 3 33 3 P d J 1 E B P G
  • 32. : 9 58 2 199A () (- . -. 4429 TA) () . .( 3 103A ( - .(+ 9 ( 4 351 04 89 48 : 9 58 2 199A ( ) -- , 8 N9 TA+ ( - -,- 9 . 4. 84 1 9168 .5 .9 42. 9168 .5 SK IM FKSTPRTKP h] bifkald [c eg A) 6 C I 4 F T P CRF C CST C F M KDM SPM TKP PR E DCS F KNCI F PKSK I 5333 RC SCETKP S P 5NCI :RPE SSK I , . )+ -Z)+ - A 8 IC NC 3 MPKTK I T PT TKCM P STC FCRF EP VPM TKP CM C TP EPF RS PR KNCI R STPRCTKP DY VPM TKP CRY S CRE 5 5187 - A+ CK 8 N T 0 RSKST T N NPRY T PRL PR KNCI R STPRCTKP 5 511 ,
  • 33. • 2CC C a • t gec gecVy ] R • C V s • kbfapKy 0 1 Y I- V r R • u 2CC C a R - 2 3 Y]K ldm n hio c P [ VN L[ 0 1 C 2 2 C 8 2 C 2 28 C 2C 3 C 2 8 .,-
  • 34. • • - - • e r p • D V I • - 43 l I n • - d 4 - ? e o m • • b g h d 4 a - - i • - -