Professional Documents
Culture Documents
Computer Vision
Naufal Suryanto
(201999137)
Table of
Background
01 One common problem in Contents
Computer Vision Task
One-Shot Learning
02 Learning from a single
training example
Siamese Network
03 Framework for learning the Face emotion recognition
similarity 2nd Presentation
Siamese Losses
04 Loss function for Siamese
network
Background
CIFAR-10 IMAGENET
MNIST
10 Classes
60.000/10.000 train/test
10 Classes >20.000 Classes
50.000/10.000 train/test > 14.000.000 images
Background
How if we just have a single training example for each
label ?
We will need to collect a lot of different images for each person
Does it works?
Background
How if we want to add new label to the model ?
Simila Not
r Similar
One-shot Learning
Learning a “similarity” function
d(img1, img2) = degree of difference between images
d(x1,y1) =
0.9
1 ) =
, y
d(x2 1
0. d(x1,
y2) =
0 .0 5
d(x2,y2) =
0.9
d(x1,
y3) =
d(x2,y3) = 1. 0
1.2
Simila Not
r Similar
One-shot Learning
If we can develop NN as a good distance function, we
will be able to solve this one-shot learning problem
Embedding vector
Embedding vector
Examples:
Deep Convolution Neural - Roundness of face
Network - Distance between eyes
- Nose width
- Check bone structure
- Jaw line length
- etc
Siamese Neural Network
Pros:
- 0 if dissimilar
Siamese Loses
1. Contrastive Loss
Siamese Loses
2. Triplet Loss
Ancho
the inputs are intentionally
weight
Deep Convolution
Network
Neural
Calculation
Loss
L(d1,d2)
r
sampled regarding Shared
weight
their class:
Distance
Calculation
Deep Convolution Neural
Neg
• We sample an anchor object, used as
Network
Siamese Loses
2. Triplet Loss
d2 d2
d1 d1
Siamese Loses
Training strategies
Offline Mining Online Mining
CNN
…
NEXT:
Face emotion recognition