brand recognition in real-life photos using deep learning - lukasz czarnecki - pydata berlin 2016
TRANSCRIPT
• Machine Learning Engineer /Data Scientist (Samsung)
• Human Tech Art founder and organiser
Łukasz Czarnecki
Monthly Actives Likes Daily Average Photos Per Day
300M
Photos shared
30B+ 2.5B 70M
0.03%0.07%4.21%
Followers engagement on brand
Source: Forrester Research, Inc.
Deep Learning
Deep Learning
Needs big amount of examples
Great results in Image
Recognition
Hard to trainLearns
features
VS VS
heavy data augmentation
&
train your network
Use pretrained network
&
SVM
Use pretrained network
&
adjust last layers
Possible approaches
NUMERIC GALLERY SAMPLE
406 420351
340 255301
Initial dataset
Adidas
Nike
Starbucks Heineken
COSTA COFFEE Carlsberg
Network propagation time
Testing different networks
VGG_S Network
Optimizing the code
Switched for batch processing
Changing framework
Caffe
~1 sec
Initial time: 2 sec
~ 200 ms ~20 ms
Getting features from Network
Training SVM on features
Testing with sliding
window
First results
68%Precission
66%Recall
Getting more data
82%Precission
68%Recall
12
34
5
Training with initial dataset
Getting more unlabeled data
Collecting windows with detections
Manual segregation
Training with bigger dataset
+500 per class
+6%
+3%
Adding normalisation
88%Precission
67%Recall
Getting features from Network
Training SVM on features
Testing with sliding
window
Normalisation
+4%
-3%
Final results
Adidas
Nike
Starbucks
COSTA COFFEE
Heineken
40%
47%
84%
80%
88%
80%
76%
93%
90%
97%
Precission Recall
Carlsberg 66%93%
88%Precission
67%Recall