https://telecombcn-dl.github.io/2017-dlcv/ Deep learning technologies are at the core of the current revolution in artificial intelligence for multimedia data analysis. The convergence of large-scale annotated datasets and affordable GPU hardware has allowed the training of neural networks for data analysis tasks which were previously addressed with hand-crafted features. Architectures such as convolutional neural networks, recurrent neural networks and Q-nets for reinforcement learning have shaped a brand new scenario in signal processing. This course will cover the basic principles and applications of deep learning to computer vision problems, such as image classification, object detection or image captioning.

1. [course site]
Visualization
#DLUPC
Amaia Salvador
amaia.salvador@upc.edu
PhD Candidate
Universitat Politècnica de Catalunya

2. 2

3. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
3

4. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
4

5. Visualize Learned Weights
AlexNet
conv1
Filters are only “interpretable” on the first layer
5

6. Visualize Learned Weights
layer 2 weights
layer 3 weights
Source: ConvnetJS
6

7. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
7

8. Activations from data
8
conv1 conv5

9. Receptive Field
Girshick et al. Rich feature hierarchies for accurate object detection and semantic segmentation. CVPR 2014
9
“people”
“text”
Visualize the receptive field of a neuron on those images that activate it the most

10. Reminder: Receptive Field
10
Receptive field: Part of the input that is visible to a neuron. It increases as we stack more
convolutional layers (i.e. neurons in deeper layers have larger receptive fields).

11. Occlusion experiments
1. Iteratively forward the same image through the
network, occluding a different region at a time.
2. Keep track of the probability of the correct class
w.r.t. the position of the occluder
Zeiler and Fergus. Visualizing and Understanding Convolutional Networks. ECCV 2015 11

12. Occlusion experiments
12
Can be applied to any arbitrary layer. “Manual” label assignment (AMT)
Zhou et al. Object detectors emerge in deep scene CNNs. ICLR 2015

13. Network Dissection
Bau, Zhou et al. Network Dissection: Quantifying Interpretability of Deep Visual Representations. CVPR 2017 13
Same idea, but automatic unit labeling using dense labeling dataset.
The thresholded activation of each conv unit in the network is evaluated for semantic segmentation.

14. Network Dissection
Bau, Zhou et al. Network Dissection: Quantifying Interpretability of Deep Visual Representations. CVPR 2017 14

15. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
15

16. Gradient-based approach
Compute the gradient of any neuron w.r.t. the image
1. Forward image up to the desired layer (e.g. conv5)
2. Set all gradients to 0
3. Set gradient for the neuron we are interested in to 1
4. Backpropagate to get reconstructed image (gradient on the image)
Visualize the part of an image that mostly activates a neuron
16

17. Gradient-based approach
1. Forward image up to the desired layer (e.g. conv5)
2. Set all gradients to 0
3. Set gradient for the neuron we are interested in to 1
4. Backpropagate to get reconstructed image (gradient on the image)
Springenberg, Dosovitskiy, et al. Striving for Simplicity: The All Convolutional Net. ICLR 2015
17

18. Gradient-based approach
Springenberg, Dosovitskiy, et al. Striving for Simplicity: The All Convolutional Net. ICLR 2015
18

19. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
19

20. Optimization approach
Simonyan et al. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, 2014
Obtain the image that maximizes a class score (or a neuron activation)
1. Forward random image
2. Set the gradient of the scores vector to be [0,0,0…,1,...,0,0]
3. Backprop to get gradient on the image
4. Update image (small step in the gradient direction)
5. Repeat
20

21. Optimization approach
Simonyan et al. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps, 2014 21

22. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
22

23. DeepDream
https://github.com/google/deepdream
23

24. DeepDream
1. Forward image up to some layer (e.g. conv5)
2. Set the gradients to equal the layer activations
3. Backprop to get gradient on the image
4. Update image (small step in the gradient direction)
5. Repeat
24

25. DeepDream
1. Forward image up to some layer (e.g. conv5)
2. Set the gradients to equal the layer activations
3. Backprop to get gradient on the image
4. Update image (small step in the gradient direction)
5. Repeat
At each iteration, the image is
updated to boost all features that
activated in that layer in the
forward pass.
25

26. DeepDream
26
More examples here

28. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
28

29. Neural Style
Style image Content image Result
29Gatys et al. Image Style Transfer Using Convolutional Neural Networks. CVPR 2016

30. Neural Style
Extract raw activations in all layers. These activations will represent the contents of the image.
30Gatys et al. Image Style Transfer Using Convolutional Neural Networks. CVPR 2016

31. Neural Style
V =
● Activations are also extracted from the style image for all layers.
● Instead of the raw activations, gram matrices (G) are computed at each layer to represent the style.
E.g. at conv5 [13x13x256], reshape to:
169
256
...
G = VT
V
The Gram matrix G gives the
correlations between filter responses.
31

32. Neural Style
match content
match style
Match gram matrices
from style image
Match activations
from content image
32Gatys et al. Image Style Transfer Using Convolutional Neural Networks. CVPR 2016

33. Neural Style
match content
match style
Match gram matrices
from style image
Match activations
from content image
33Gatys et al. Image Style Transfer Using Convolutional Neural Networks. CVPR 2016

34. Neural Style
34Gatys et al. Image Style Transfer Using Convolutional Neural Networks. CVPR 2016

35. Neural Style
35Gatys et al. Image Style Transfer Using Convolutional Neural Networks. CVPR 2016
A year later...

36. 36
Content Image Style Image Result
Luan et al. Deep Photo Style Transfer. arXiv Apr 2017

37. 37
Content Image Style Image Result
Luan et al. Deep Photo Style Transfer. arXiv Apr 2017

38. Visualization
● Learned weights
● Activations from data
● Gradient-based
● Optimization-based
● DeepDream
● Neural Style
38

39. Resources
● ConvnetJS
● Deepvis toolbox
● DrawNet from MIT: Visualize strong activations & connections between units
● 3D Visualization of a Convolutional Neural Network
● Latest NeuralStyle in torch
● Keras examples:
○ Optimization-based visualization Example in Keras
○ DeepDream in Keras
○ NeuralStyle in Keras
● Picasso: visualization tool (supports keras models - use it in your projects !)
○ blog post to convince you here
39

40. Questions?

41. t-SNE
Embed high dimensional data points
(i.e. feature codes) so that pairwise
distances are preserved in local
neighborhoods.
Maaten & Hinton. Visualizing High-Dimensional Data using t-SNE.
Journal of Machine Learning Research (2008).
41

42. t-SNE
Can be used with features from layer before classification
42

43. Optimization approach
Bojarski et al. VisualBackProp: efficient visualization of CNNs. arXiv May 2017
Value-based backpropagation
43