Data Science Stack Exchange
Data Science Stack Exchange

Questions tagged [convolution]

For use when discussing the commutative and linear, but not associative operator interpreted on functions and distributions.

The convolution of the functions $f(t)$, $g(t)$ (interpreted on $]-\infty,\infty[$) is defined as

$$(f * g)(t)=\int_{-\infty}^{\infty} f(t)g(x-t)dt$$

Or in the discrete case,

$$(f * g)(n) = \sum_{k \in D} f(k) g(n - k)$$

enter image description here

287 questions
282
votes
12 answers

What are deconvolutional layers?

I recently read Fully Convolutional Networks for Semantic Segmentation by Jonathan Long, Evan Shelhamer, Trevor Darrell. I don't understand what "deconvolutional layers" do / how they work. The relevant part is 3.3. Upsampling is backwards strided…
Martin Thoma
  • 18,630
  • 31
  • 92
  • 167
80
votes
5 answers

What is the difference between "equivariant to translation" and "invariant to translation"

I'm having trouble understanding the difference between equivariant to translation and invariant to translation. In the book Deep Learning. MIT Press, 2016 (I. Goodfellow, A. Courville, and Y. Bengio), one can find on the convolutional…
Aamir
  • 963
  • 1
  • 7
  • 6
29
votes
1 answer

What is the difference between upsampling and bi-linear upsampling in a CNN?

I am trying to understand this paper and am unsure of what bi-linear upsampling is. Can anyone explain this at a high-level?
JGG
  • 503
  • 1
  • 5
  • 7
28
votes
3 answers

Why convolutions always use odd-numbers as filter size

If we have a look to 90-99% of the papers published using a CNN (ConvNet). The vast majority of them use filter size of odd numbers:{1, 3, 5, 7} for the most used. This situation can lead to some problem: With these filter sizes, usually the…
Jonathan DEKHTIAR
  • 590
  • 2
  • 5
  • 10
18
votes
2 answers

In CNN, why do we increase the number of filters in deeper Convolution layers for complex images?

I have been doing this online course Introduction to TensorFlow for AI, ML and DL. Here in one part, they were showing a CNN model for classifying human and horses. In this model, the first Conv2D layer had 16 filters, followed by two more Conv2D…
Sanjay Saha
  • 193
  • 1
  • 1
  • 8
15
votes
1 answer

What is a 1D Convolutional Layer in Deep Learning?

I have a good general understanding of the role and mechanism of convolutional layers in Deep Learning for image processing in case of 2D or 3D implementations - they "simply" try to catch 2D patterns in images (in 3 channels in case of 3D). But…
Hendrik
  • 8,377
  • 17
  • 40
  • 55
14
votes
3 answers

What is the difference between Dilated Convolution and Deconvolution?

These two convolution operations are very common in deep learning right now. I read about dilated convolutional layer in this paper : WAVENET: A GENERATIVE MODEL FOR RAW AUDIO and De-convolution is in this paper : Fully Convolutional Networks for…
Shamane Siriwardhana
  • 827
  • 1
  • 8
  • 25
12
votes
3 answers

Relation between convolution in math and CNN

I've read explanation of convolution and understand it to some extent. Can somebody help me understand how this operation relates to convolution in Convolutional Neural Nets? Is filter like function g which applies weight?
noname7619
  • 323
  • 2
  • 9
10
votes
1 answer

What is fractionally-strided convolution layer?

In paper Generating High-Quality Crowd Density Maps using Contextual Pyramid CNNs, in Section 3.4, it said Since, the aim of this work is to estimate high-resolution and high-quality density maps, F-CNN is constructed using a set of …
Haha TTpro
  • 233
  • 1
  • 2
  • 7
10
votes
2 answers

How can I detect blocks of text from scanned document images

ORIGINAL IMAGE: GOAL: I want to separate texts into individual paragraphs by placing bounding boxes over them (as shown above). I tried it do this via traditional computer vision approach using opencv. I plotted character level bounding…
DGS
  • 291
  • 1
  • 3
  • 7
9
votes
3 answers

Convolutional Neural Networks layer sizes

I am trying to understand an article Backpropagation In Convolutional Neural Networks But I can not wrap my head around that diagram: The first layer has 3 feature maps with dimensions 32x32. The second layer has 32 feature maps with dimensions…
koryakinp
  • 436
  • 1
  • 5
  • 14
9
votes
1 answer

How to train data by batch from disk?

I am working on a convolutional neural network for image classification. The training dataset is too large to be loaded on my computer memory (4gb), on top of that I also need to try some augmentation to balance the classes. I am using keras. I have…
Learning is a mess
  • 646
  • 1
  • 8
  • 16
9
votes
2 answers

Ways to reconstruct shuffled pixels of a video file?

Suppose that you have a video file which pixel order has been shuffled once. That is, a random order have been defined once and applied to all frames. Does it exist some known approach for retrieving the initial order of pixels? I have some ideas…
Denis Dollfus
  • 93
  • 3
8
votes
4 answers

Understanding how convolutional layers work

After working with a CNN using Keras and the Mnist dataset for the well-know hand written digit recognition problem, I came up with some questions about how the convolutional layer work. I can understand what the convolution process is. My first…
Karampistis Dimitrios
  • 93
  • 4
8
votes
1 answer

GAN vs DCGAN difference

I am trying to understand the key difference between GAN and DCGAN. I know that DCGAN uses a convolutional network. But: What data is better to push into GAN and what data fits better to DCGAN? Does DCGAN work better with small data dimensions?
CezarySzulc
  • 257
  • 3
  • 10
1
2 3
…
19 20