55
votes
Accepted
Is deep learning killing image processing/computer vision?
On the top of this answer, you can see a section of updated links, where artificial intelligence, machine intelligence, deep learning or and database machine learning progressively step of the grounds ...
22
votes
Is deep learning killing image processing/computer vision?
First, there is nothing wrong with doing grad work in image processing or computer vision and using deep learning. Deep learning is not killing image processing and computer vision, it is merely the ...
13
votes
Is deep learning killing image processing/computer vision?
No Deep Learning isn't killing Image Processing. You need huge datasets and lots of computational resources to do deep learning. There are plenty of applications where it is desirable to be able to do ...
13
votes
Is deep learning killing image processing/computer vision?
Today we had a discussion with a friend of mine. It was a rainy day here in Munich, while a large portion of Europe was having a kind of sunny atmosphere. People were sharing photographs in social ...
10
votes
Accepted
When is a network called end-to-end training?
From feature extraction to learning the desired result, deep learning algorithms can act as full pipelines for solving tasks at hand. End-to-end learning usually refers to omitting any hand-crafted ...
9
votes
A Machine Learning Based Algorithm as an Alternative to the Matched Filter
Sure, you can learn the matched filter, as convolution with a filter is just a function applied to a signal, and e.g. Neural Networks (through the universal approximation theorem) are good function ...
8
votes
Is deep learning killing image processing/computer vision?
The short answer is, No. DL can recognize a mug in a photo, but this doesn't kill signal processing in anyway. That said, your question is quite relevant in these troubled days. There is a nice panel ...
7
votes
Can deep neural networks achieve real-time video analysis?
Nvidia seems to have published some white papers comparing DNN inference performance between high-powered CPUs and (of course) Nvidia GPUs. (one example)
Ballpark seems to be that some systems can ...
7
votes
Accepted
A Machine Learning Based Algorithm as an Alternative to the Matched Filter
The idea is to have a simple experiment to see if we can get, for a known signal, a better results than the Matched Filter for time delay estimation.
Experiment Objective
Generate, using ML (DL) a ...
6
votes
Is deep learning killing image processing/computer vision?
Data engineering is still used in machine learning to preprocess and select the data fed to DNNs to improve their learning time and their evaluation efficiency. Image processing (the stuff between ...
6
votes
Accepted
Classic Signal Processing vs Deep Learning / Machine Learning (DNN / ML) Based Signal Processing
This is an open discussion.
In my opinion, any field we couldn't figure near optimal solution (And in most cases we only have Linear Optimal solution) using Deep Learning will replace classic methods ...
6
votes
Accepted
When to Use Composite Filters and When to Use Separable Filters?
Image Processing Context
In classic Image Processing the filters used are known.
Hence being separable is a property of a given filter which is suitable to the task.
In this context, separability only ...
6
votes
Accepted
Which Programming Language Should Be Used for Deep Learning (Deep Neural Network [DNN])?
The language choice depends on many factors.
For instance, are you after developing low level features of DNN or using existing building blocks?
Most advanced and popular Deep Neural Networks (DNN) ...
5
votes
Is deep learning killing image processing/computer vision?
A thorough understanding of signal processing (along with linear algebra, vector calculus, mathematical statistics etc.) is imo indispensable for non-trivial work in the field of deep learning, ...
5
votes
Principal Component Analysis (PCA) on Convolutional Neural Network (CNN) Features
I'm not into details of this specific case but I can see some logic.
A convolution layer can be reformulated as a Matrix Multiplication:
$$ y = W x $$
Let's say we trained on Data Set $ {x}^{1} $ ...
5
votes
Neural Networks and Complex Valued Inputs
The power of complex representations remains an open topic to me. I still do strive the understand Fourier transformations.
An underlying question is, to me: why would complex transformations be ...
5
votes
Accepted
How to Remove the Patch Artifacts of Neural Network Denoising Process?
One simple way to solve it is using Overlapping Patches.
Let's say you have image which is $ 20 \times 20 $ and you work on patches of the size $ 5 \times 5 $.
As I understand from your description ...
5
votes
Accepted
The Meaning of $ \mathbb{E} $ Operator in the Pix2Pix Loss Formula of a Neural Network / Convolutional Neural Network
The operator $ \mathbb{E} \left[ \cdot \right] $ is the Expectation Operator.
In the context above it means you run over all the pairs of x, y and average the ...
5
votes
Accepted
Explain the Process of Spectral Pooling and Spectral Activation in the Context of CNN in Frequency Domain
Wouldn't this be equivalent to discarding all those frequencies in the input layer?
No, it won't for 2 facts:
Just like a CNN isn't a linear regression due to having non linear function in between. ...
5
votes
Accepted
Image Segmentation Using Deep Learning
Well, I think the best way to tackle this question is a little background and a code as an example. I chose MATLAB for this example though PyTorch / Keras would probably be as easy.
This task requires ...
5
votes
Accepted
When a face collapses into a swirling black hole on a video conference call like this is it due to some advanced AI-based error-correction gone wrong?
This looks like what pretty "classical" video compression does when facing severe data loss – notice the very MPEG-typical square blocks, and how some of the probably more changing blocks ...
4
votes
Accepted
Deep Learning: Classification vs. Convolution for Signal Restoration
By deep learning, I'll assume you mean neural network. To develop a neural network, you'll need labeled data. This means you need a bunch of example inputs ($r$) and outputs ($X$). Once you have that, ...
4
votes
Accepted
Perform Transposed Convolution in Spectral / Frequency Domain?
Basically, if we define convolution as $ y = h \ast x $, it can be written in Matrix form (See Generate the Matrix Form of 1D Convolution Kernel):
$$ \boldsymbol{y} = H \boldsymbol{x} $$
Transposed ...
4
votes
Image Standardization for Image Classification (Machine / Deep Learning)
I will display image standardization using MATLAB:
...
3
votes
Is deep learning killing image processing/computer vision?
My perspective from university was that many signal processing people were a bit hostile toward ML, I suspect because they felt threatened that it was encroaching on their domain. But recently there's ...
2
votes
Is deep learning killing image processing/computer vision?
Many people, including Andrew Ng in his Deep Learning Specialization, emphasize the importance of domain knowledge and developing hand crafted features. Only then one can achieve significant ...
2
votes
Is deep learning killing image processing/computer vision?
Well, yes. In the same way that the development in higher level programming languages like C++ and Python 'killed' assembly programming. That does not mean it is irrelevant to learn assembly when you ...
2
votes
Can deep neural networks achieve real-time video analysis?
Here is a newly published paper and video example:
https://www.youtube.com/watch?v=w2iV8gt5cd4
http://arxiv.org/abs/1411.4389
Only top scored, non community-wiki answers of a minimum length are eligible
Related Tags
deep-learning × 69machine-learning × 25
image-processing × 19
computer-vision × 15
neural-network × 13
signal-analysis × 8
speech-recognition × 8
convolution × 7
audio × 5
python × 4
image-segmentation × 4
stft × 4
speech-processing × 4
artificial-intelligence × 4
matlab × 3
fourier-transform × 3
audio-processing × 3
real-time × 3
classification × 3
filters × 2
discrete-signals × 2
filter-design × 2
spectrogram × 2
mfcc × 2
3d × 2