Questions tagged [convolution]

For questions related to the convolution operation in mathematics, convolutional neural networks, image processing and computer vision.

Filter by
Sorted by
Tagged with
9
votes
2answers
1k views

Why would you implement the position-wise feed-forward network of the transformer with convolution layers?

The Transformer model introduced in "Attention is all you need" by Vaswani et al. incorporates a so-called position-wise feed-forward network (FFN): In addition to attention sub-layers, each of the ...
7
votes
2answers
1k views

When should I use 3D convolution?

I am new to convolutional neural networks, and I am learning 3D convolution. What I could understand is that 2D convolution gives us relationships between low-level features in the X-Y dimension, ...
6
votes
1answer
425 views

What are the benefits of using max-pooling in convolutional neural networks?

I am reading Francois Chollet's Deep learning with Python, and I came across a section about max-pooling that's really giving me trouble. I am unable to copy-paste the content, so I've included ...
4
votes
2answers
330 views

How to calculate the number of parameters of a convolutional layer?

I was recently asked at an interview to calculate the number of parameters for a convolutional layer. I am deeply ashamed to admit I didn't know how to do that, even though I've been working and using ...
4
votes
3answers
360 views

Convolutional Neural Network: does each filter in each convolution layer create a new image?

Say I have a CNN with this structure: input = 1 image (say, 30x30 RGB pixels) first convolution layer = 10 5x5 convolution filters second convolution layer = 5 3x3 convolution filters one dense layer ...
4
votes
2answers
286 views

Wouldn't convolutional neural network models work better without flattening the input in any stages?

The above model is what really helped me understand the implementation of convolutional neural networks, so based on that, I've got a tricky hypothesis that I want to find more about, since actually ...
4
votes
2answers
73 views

Is there any difference between the convolution operation applied to images and applied to other numerical 2D data?

Is there any difference between the convolution operation applied to images and applied to other numerical 2D data? For example, we have a pretty good CNN model trained on a number of $64 \times 64$ ...
4
votes
1answer
237 views

Combining mean pooling and max pooling

Is it popular or effective to concatenate the results of mean-pooling and max-pooling? To get the invariance of the latter and the expressivity of the former.
4
votes
2answers
406 views

When is max pooling exactly applied in convolutional neural networks?

When using convolutional networks on images with multiple channels, do we max pool after we sum the feature map from each channel, or do we max pool each feature map separately and then sum? What's ...
4
votes
1answer
240 views

What is the difference between asymmetric and depthwise separable convolution?

I have recently discovered asymmetric convolution layers in deep learning architectures, a concept which seems very similar to depthwise separable convolutions. Are they really the same concept with ...
3
votes
1answer
64 views

Is it useful to eliminate the less relevant filters from a trained CNN?

Imagine I have a tensorflow CNN model with good accuracy but maybe too many filters: Is there a way to determine which filters have more impact in output? I think it should be possible. At least, if ...
3
votes
1answer
58 views

How is the convolution layer is usually implemented in practice?

Following an earlier question, I'm interested in understanding the basics of Conv2d and especially how the kernel is applied, summed, and the propagated. I ...
3
votes
1answer
39 views

Is it possible to vectorise a CNN?

I am trying to write a CNN from scratch and am wondering if it possible to vectorise the convolution step. For example, if I had a dataset of 500 RGB images of size 32x32x3, and wanted the first conv ...
2
votes
1answer
26 views

Is it a sign of overfitting when validation_loss dips and then goes up with increasingly bigger swings?

I am experimenting with a ConvNet to categorize images taken with a depth camera. So far I have 4 sets of 15 images each. So 4 labels. The original images are 680x880 16-bit grayscale. They are scaled ...
2
votes
1answer
100 views

Can I shuffle image channel data as a form of data augmentation?

If I want to augment my dataset, is shuffling or permuting the channels (RGB) of an image a sensible augmentation for training a CNN? IIRC, the way convolutions work is that a kernel operates over ...
2
votes
2answers
63 views

Why do we get a three-dimensional output after a convolutional layer?

In a convolutional neural network, when we apply the convolution on a $5 \times 5$ image with $3 \times 3$ kernel, with stride $1$, we should get only one $4 \times 4$ as output. In most of the CNN ...
2
votes
1answer
30 views

Is it possible to apply the associative property of the convolution operation when it is followed by a non-linearity?

The associative property of multidimensional discrete convolution says that: $$Y=(x \circledast h_1) \circledast h_2=x\circledast(h_1\circledast h_2)$$ where $h_1$ and $h_2$ are the filters and $x$ is ...
2
votes
1answer
121 views

How can the convolution operation be implemented as a matrix multiplication?

How can the convolution operation used by CNNs be implemented as a matrix-vector multiplication? We often think of the convolution operation in CNNs as a kernel that slides across the input. However, ...
1
vote
2answers
86 views

Do convolutional neural networks perform convolution or cross-correlation?

Typically, people say that convolutional neural networks (CNN) perform the convolution operation, hence their name. However, some people have also said that a CNN actually performs the cross-...
1
vote
1answer
50 views

How do I optimize the number of filters in a convolution layer?

I’m trying to figure out how to write an optimal convolutional neural network with respect to maximizing and minimizing filters in a convolution 2D layer. This is my thinking and I’m not sure if it's ...
1
vote
1answer
37 views

Convolutional filters: create new ones

I'm studying a Master's Degree in Artificial Intelligence an my final work is about Convolutional Neuronal Networks. I was looking for information about filters (or kernel) at the convolutional ...
1
vote
1answer
21 views

How will the input be preserved as we go deeper in CNN, where dimensions decrease drastically?

Our length of our like feature representation actually decreases as we go deeper into the CNN, I mean to say that horizontal and vertical lengths decrease while depth(channels) increase. So, how will ...
1
vote
1answer
28 views

Are activation functions applied to feature maps?

If I have a convolutional neural network, and I convolve my input tensor with a kernel, the output is a feature map. Is an activation function then applied to this feature map? If its an image that ...
1
vote
1answer
76 views

How is the depth of filters of hidden layers determined?

I am a bit confused on the layer depth of later convolutional filters. At layer 1 there are usually 40 or so 3x3x3 filters. Each of these filters outputs a 2d array so the total output of the first ...
1
vote
1answer
621 views

Is my understanding of how the convolution with stride 2 works in this example correct?

I'm currently reading this explanation of convolutional neural networks and there's a part around strides that I don't quite understand. I'm just starting with this, so I apologize if this is a really ...
1
vote
0answers
11 views

Is there a difference between using 1d conv layers and 2d conv layers with kernel with size of 1 along other than time dimension?

Let's assume I use convolutional networks for time-series prediction. Data I feed to the network have 1 channel depth, height of number of periods and number of features is the width, so the frame ...
1
vote
0answers
21 views

How do we choose the filters for the convolutional layer of a convolution neural network?

Since the hidden layers of a CNN work as a trainable feature extractor, more detailed content based on a larger number of pixels shall require bigger filter sizes. But for cases where localized ...
1
vote
0answers
120 views

What's the difference in using multiple convolutional layers and no pooling versus using a single convolutional layer and a single max pooling layer?

I'm currently working on a college project in which I'm designing a Deep Q-Network that takes images/frames as an input. I've been searching online to see how other people have designed their ...
1
vote
0answers
20 views

Efficient implementation of seperable convolution in tensorflow [closed]

It seems like the native implementation of separable convolution in tensorflow is not efficient. https://github.com/tensorflow/tensorflow/issues/12940 Is anyone aware how can we get an efficient ...
1
vote
1answer
68 views

Why does Convolutional layer unde usually has the same input/output channel size?

As famous model VGG16 shows(and other famous models), The convolutional layers before pooling usually have the same input and output channel sizes? What's the reason for that? Is there a theory or ...
0
votes
1answer
42 views

Set my own kernels to a CNN and don't let it to modify it

I'm newbie in Convolutional Neural Networks and I have discovered (and I hope I'm right) that kernels in convolutional layers are learned while training. If I have a kernel that it is very good to ...
0
votes
0answers
8 views

Looking for the right type of 1D-Convolution that only considers one column/attribute

My input has the shape of n rows (time steps) and m columns (attributes). I want to train a convolutional neural network on it to predict a class. I am currently using 1D-Convolutions. I got a good ...
0
votes
2answers
329 views

How should the values of the filters of a CNN change?

I wrote a convolutional neural network for the MNIST dataset with Numpy from scratch. I am currently trying to understand every part and calculation. But one thing I noticed was the "just positive" ...