Beruflich Dokumente
Kultur Dokumente
jefersson@dcc.ufmg.br
DCC
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Roteiro da Aula
1 Supervised Classification
3 Segmentação Semântica
Context Window-Based Approach
Fully Convolutional Neural Network
2 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Pattern Classifier
Typical Steps
Building
Multimedia Pattern
Feature Classifier
Dataset Representation Training
Extraction
3 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Pattern Classifier
Typical Steps
Building
Multimedia Pattern
Feature Classifier
Dataset Representation Training
Extraction
Example
3 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Pattern Classifier
Typical Steps
Building
Multimedia Pattern
Feature Classifier
Dataset Representation Training
Extraction
3 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Pattern Classifier
Typical Steps
Building
Multimedia Pattern
Feature Classifier
Dataset Representation Training
Extraction
Using
3 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
K-Nearest Neighbor
4 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
K-Nearest Neighbor
4 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
K-Nearest Neighbor
4 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
K-Nearest Neighbor
4 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
K-Nearest Neighbor
4 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Decision Trees
5 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
Decision Trees
5 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
6 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
6 / 46
DCC029/868 - Processamento Digital de Imagens
Supervised Classification
6 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Roteiro da Aula
1 Supervised Classification
3 Segmentação Semântica
Context Window-Based Approach
Fully Convolutional Neural Network
7 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Challenges:
1 Deep learning needs large amount of data to train
2 Many applications (e.g. remote sensing) typically has small amount of annotated
data
8 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Challenges:
1 Deep learning needs large amount of data to train
2 Many applications (e.g. remote sensing) typically has small amount of annotated
data
Research Questions:
1 Is it possible to transfer features from every-day pics to the remote sensing
domain?
2 Do transferred features more effective than fully-trained?
3 How to better exploit deep learning in remote sensing data?
Reference
K. Nogueira, O. A. B. Penatti and J. A. dos Santos. Towards better exploiting convolutional neural networks for remote sensing scene classification. Pattern Recognition, 61,
539-556, 2017.
8 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
1 - Fully Training
Training from scratch
Target Dataset
9 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
1 - Fully Training
Training from scratch
classification
Target Dataset
...
conv
conv
conv
fully
fully
9 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
1 - Fully Training
Training from scratch
classification
Target Dataset
...
conv
conv
conv
fully
fully
9 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
Random Initialized ConvNet
Original Dataset
classification
conv
...
conv
conv
fully
fully
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
Random Initialized ConvNet
Original Dataset
classification
conv
...
conv
conv
fully
fully
Target Dataset
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
Random Initialized ConvNet
Original Dataset
classification
conv
...
conv
conv
fully
fully
Target Dataset
...
conv
conv
conv
fully
fully
Fine-Tuning ConvNet
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
Random Initialized ConvNet
Original Dataset
classification
conv
...
conv
conv
fully
fully
Target Dataset
...
conv
conv
conv
fully
fully
Fine-Tuning ConvNet
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
Random Initialized ConvNet
Original Dataset
classification
conv
...
conv
conv
fully
fully
Transfer of
trained weights
Target Dataset
...
conv
conv
conv
fully
fully
Fine-Tuning ConvNet
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
Random.Initialized.ConvNet
Original.Dataset
classification
conv
...
conv
conv
fully
fully
Transfer.of. Different.number.of.
trained.weights classes⇒no.weight.
transfer
classification
Target.Dataset
...
conv
conv
conv
fully
fully
Fine-Tuning.ConvNet
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
2 - Fine-Tuning
RandomPInitializedPConvNet
OriginalPDataset
classification
conv
...
conv
conv
fully
fully
TransferPofP DifferentPnumberPofP
trainedPweights classes⇒noPweightP
transfer
classification
TargetPDataset
...
conv
conv
conv
fully
fully
Fine-TuningPConvNet
PossiblePLayersPtoP
Freeze
10 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
3 - Feature Extractor
Pre-trained ConvNet
classification
...
conv
conv
conv
fully
fully
11 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
3 - Feature Extractor
Pre-trained ConvNet
classification
...
conv
conv
conv
fully
fully
deep feature
vector
11 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Strategies to Exploit ConvNets
3 - Feature Extractor
Pre-trained ConvNet
classification
...
conv
conv
conv
fully
fully
deep feature classification
vector (SVM)
11 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
Datasets
Examples
12 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
Some Experiments
13 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
100
90
Average accuracy (%)
80
70
60
50
40
LCH
BIC
I
LAS
ACC
et
Ove sm k
BS 5k
VG et
G9
G9
G9
sm0k
Caf eNet
ha k
s k
SAS
Ale atL
Goo G16
Ove eatS
HO 20
HO 40
BD 810
BS 10
sm
BD 5
BD 1m
GIS
feN
xN
r Fe
HO
rF
gL
Feature representation
UCMerced Land-use Dataset
14 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
100
90
Average accuracy (%)
80
70
60
50
40
LCH
BIC
I
LAS
ACC
et
Ove sm k
BS 5k
VG et
G9
G9
G9
G9
ha 00
sm0k
Caf eNet
s k
SAS
Ale eatL
Goo G16
Ove eatS
HO 14
HO 20
HO 40
BD 180
BS 1m0
BD 5
BD 1m
GIS
feN
xN
s
HO
rF
rF
gL
Feature representation
RS19 Dataset
15 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
100
90
Average accuracy (%)
80
70
60
50
40
LCH
BIC
I
LAS
ACC
et
Ove sm k
BS 5k
BS 5k
VG et
G9
G4 9
sm0k
Caf Net
smk
SAS
Ale atL
Goo 16
Ove eatS
HO 20
BD 50
BS 10
sm
sw
GIS
G
BD 1
feN
xN
r Fe
HO
gL e
rF
Feature representation
Brazilian Coffee Scenes Dataset
16 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
17 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
18 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
RS19 Dataset
19 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
20 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
missclassified
Medium Residential −−−−−−−→ Dense Residential
into
21 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
missclassified
Commercial −−−−−−−→ Park
into
22 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
23 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
24 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
RS19 Dataset
25 / 46
DCC029/868 - Processamento Digital de Imagens
Deep Vs Hand-Crafted Features
Experimental Analysis
26 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Roteiro da Aula
1 Supervised Classification
3 Segmentação Semântica
Context Window-Based Approach
Fully Convolutional Neural Network
27 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Semantic Segmentation
(Aka: Pixelwise classification)
28 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Semantic Segmentation
(Aka: Pixelwise classification)
29 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Context Window-Based Approach
pixel to be
classified
Reference
K. Nogueira, M. Dalla Mura, J. Chanussot, W. R. Schwartz, J. A. dos Santos. Learning to semantically segment high-resolution remote sensing images. In: 2016 23rd
International Conference on Pattern Recognition (ICPR), 2016, Cancun.
30 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Context Window-Based Approach
ConvNet
...
31 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Context Window-Based Approach
Datasets
Agriculture Dataset
(r) Image
(s) Ground-Truth
32 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Context Window-Based Approach
Some Results
Agriculture Dataset
33 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Fully-Convolutional Networks
Deep learning can learn global and local semantic information
Main contributions of the paper:
Fully Convolutional Neural Network (FCN)
Based on fine-tuning networks
Reference
J. Long, E. Shelhamer, T. Darrell. Fully convolutional networks for semantic segmentation. CVPR, p. 3431-3440, Boston, USA, 2015
34 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
35 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
36 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
37 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
38 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
39 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
40 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Experiments
Metrics
41 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Results
Pascal VOC 2011,2012
42 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Results
NYUDv2
43 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Results
SIFT Flow Dataset
44 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Results
Pascal VOC
45 / 46
DCC029/868 - Processamento Digital de Imagens
Segmentação Semântica
Fully Convolutional Neural Network
Conclusion
46 / 46