Questions tagged [deep-learning]
The deep-learning tag has no usage guidance.
85
questions
0
votes
0
answers
15
views
How to impose power constraint on an encoder's output while training a deep NN?
A deep encoder which takes in a 4 bit input gives out an 8-dimensional vector. If I want the power of this 8-D vector constrained to be 1, then I should multiply all the elements by A/B? Where A is ...
0
votes
0
answers
45
views
How to calculate the derivative of a sequence (discrete function) with respect to another discrete function?
In Learning Recursive Filters for Low-Level Vision via a Hybrid Neural Network, the hidden state of the recurrent neural network (RNN), after some simplification, presented as
$$
h[k] = (1-p)\cdot x[k]...
5
votes
1
answer
86
views
What architecture of CNN to solving a image regression problem (case study: solving Poisson equation)?
I've been working on solving Poisson problem using CNN model (you can ignore Poisson problem part if you not familiar and jump to image processing/CNN part). More specific, I am solving electric ...
0
votes
0
answers
25
views
Segmenting audio in its different parts using deep learning
I am trying to segment a song into its different parts. In pop music, it's common for a song to have a verse and a chorus. And they repeat. So it should be possible to use deep learning to find the ...
4
votes
1
answer
70
views
How to Estimate a Multi Channels and Multi Kernels Convolution Kernel (Deep Learning Style) Given the Input and Output Images
Is it possible that can estimate convolutional kernel that have multi channels and multi filters ?
I saw answer from this to link to estimate kernel for one channel and one filter (Estimating ...
1
vote
1
answer
59
views
preparing the ct scan data of a patient, using a visible feature in the mri image
A dataset of mri and ct scan images of patients has been prepared. There is a feature /damaged area/ in the mri image that is easily visible. But the injury of this area is not visible in the CT scan ...
5
votes
1
answer
145
views
Bibliographic References on Denoising Distributed Acoustic data with Deep Learning
Distributed Acoustic Sensing (DAS)
I have an iDAS (intelligent distributed acoustic sensing) dataset obtain from an undersea optical fibre. iDAS data have a 2D dimensional representation. On the one ...
0
votes
0
answers
31
views
Object detection only when a particular type of object is on the image
Apologies if this has been answered already.
I am very new to computer vision. I am kind of familiar with object detection and classification for many types of classes, which involves training data ...
3
votes
1
answer
57
views
Edge / Pixel Type (Homogenous, Edge, Texture) Classification as Part of an Image Denoising Procedure
For most noise reduction algorithm, the same process is applied to every pixel no matter
the pixel belongs to one of three types of pixels such as homogeneous regions, edges or textures.
Different ...
5
votes
2
answers
236
views
A self-supervised learning technique to denoise my specific signal
So I work in this domain of biophysics that has to do with a light-based detection for measuring small movement of molecules (nanometer and piconewton scale) via a Quadrant Photodiode. This signal ...
5
votes
1
answer
85
views
Relationship / Connection Between Machine Learning / Deep Learning and Computer Vision [closed]
What is the actual relationship between Machine learning and Computer vision? Is Computer vision is subset of Machine learning or is it another independent subset of Machine Learning? I am trying to ...
1
vote
1
answer
60
views
Fixing/up-rezzing images is easily possible these days in practice. Is there any analogous tool available for low-quality audio?
Tools like waifu2x and Anime4k (for the MPV video player) can already easily de-noise and up-rez low quality images to 4k quality pretty darn well. Similar tools like DLSS and FSR are used for video ...
3
votes
1
answer
37
views
Explain the Terms: Semantically Richer and Spatially More Precise in the HRNet Model Paper
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
From HR-Nets we get semantically ...
1
vote
1
answer
43
views
Decision level fusion
I have trained three deep learning models, and used majority voting for the final decision. Applying majority voting has led to improving the accuracy of the classifier with all test samples, except ...
1
vote
0
answers
80
views
Labels in speaker verification
I'm a beginner.
If I am using a Convolutional Neural Networks with Triplet Loss as a loss function (also combined with GAN and a Classifier) for building a model that performs Speaker Verification, ...
7
votes
2
answers
1k
views
A Machine Learning Based Algorithm as an Alternative to the Matched Filter
Consider we have to detect a known signal added with Gaussian noise. In this scenario, the matched filter is known to be an optimal filter for SNR. The question: is there any machine learning ...
0
votes
3
answers
345
views
Is it possible to classify signal samples using STFT without (image-based) spectrograms?
I am aiming to conduct a classification-based study using signals collected from various devices. I've researched other approaches which make use of STFT for producing a spectrogram for speech and EEG/...
4
votes
1
answer
68
views
Image Standardization for Image Classification (Machine / Deep Learning)
I am trying to write a program to standardize an image which I need to better perform image classification. I found the definition of standardisation which is obtained simply by subtracting the mean ...
0
votes
1
answer
246
views
How to convert depth to disparity
if $k = \text{baseline}\cdot\text{focal length}$ is known, then the disparity is the ratio of $k$ to depth $d_\text{image}$:
$$D_\text{image} = \frac{k}{d_\text{image}}$$
I have a ...
1
vote
1
answer
46
views
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?
Within this newscast video1 a video conference call is shown. Between 02:23 and 02:37 the face of the interviewee appears to get ...
6
votes
3
answers
1k
views
Role of window length and overlap in uncertainty principle?
I am trying to predict epilepsy using spectrograms and a convolutional neural network.
So far I have achieved a validation accuracy of 86% which i feel like is pretty good. Lots of the papers doing ...
2
votes
2
answers
572
views
How to train a FCNN with Spectrogram images?
I'm working on a audio dereverberation deep learning model, based on the U-net architecture.
The idea of my project came from image denoising with auto-encoders. I feed the reverberated spectrogram to ...
1
vote
1
answer
146
views
Image Segmentation Using Deep Learning
I see in many reviews on Autonomous Car how they segment the images with person, cars, etc...
How is it achieved in Deep Learning?
Could anyone give an example of that?
How it is done?
0
votes
0
answers
28
views
How can I speech enhancement with DNN?
I want to do speech enhancement with DNN on Matlab. I downloaded the TIMIT dataset from the internet as a .wav file. I also downloaded the noises from the Noisex-92 database as .m file. Now I need to ...
1
vote
2
answers
65
views
How to choose a deep learning model?
I have split the database available into 70% training, 15% validation, and 15% test. I have trained the model and got the following results:
training accuracy 100%, validation accuracy 97.61%, test ...
4
votes
1
answer
147
views
Which Programming Language Should Be Used for Deep Learning (Deep Neural Network [DNN])?
I will do voice activity detection and speech enhancement based deep neural network. However, I don't know whether to do this via matlab or pyhton. In which programming language can I find more ready-...
4
votes
2
answers
186
views
When to Use Composite Filters and When to Use Separable Filters?
I’m a beginner in image processing, and was wondering since seperated (decomposed) filters help give faster and more efficient results, when do we even need to use composite filters? All I heard is ...
5
votes
2
answers
483
views
Explain the Process of Spectral Pooling and Spectral Activation in the Context of CNN in Frequency Domain
I am reading the paper Design of an energy efficient accelerator for training of convolutional neural networks using frequency Domain Computation:
which uses Frequency Pooling, from Spectral ...
0
votes
0
answers
53
views
I have two signals, recorded from the same device. How do I standardize/normalise them?
I essentially have two signals X and Y, recorded with PPG devices. These have been filtered already. I want to standardize(z-score) or min-max scale them but I don't know if I should do this on each ...
0
votes
0
answers
31
views
Signal patterns between train and test sets are vastly inconsistent
I am trying to build a machine learning classification model of a given signal dataset of 3 classes (one file for train signal data is another one for test data). I tried different machine learning ...
5
votes
1
answer
142
views
Can we use AutoEncoder for Sparse Sensing?
Is there a way to introduce sparsity constraint on an autoencoder to achieve compressions in the Cosine/Fourier domain? I want to use the encoder part of the Auto encoder as the feature extractor from ...
0
votes
1
answer
62
views
Classification of very noisy EMG signals
I'm an absolutely newbie to signal processing. I'm trying to classify EMG signals which are very noisy (decibel values are more than -70 dB in some cases). After applying EMD technique these values ...
4
votes
1
answer
254
views
Perform Transposed Convolution in Spectral / Frequency Domain?
I'm doing some experimentation on performing end to end generative modeling in the frequency domain. I've got a working convolutional layer, but do not yet have a Conv2DTranspose equivalent. Please ...
4
votes
1
answer
76
views
The Meaning of $ \mathbb{E} $ Operator in the Pix2Pix Loss Formula of a Neural Network / Convolutional Neural Network
I've been observing the Pix2Pix Paper - Image to Image Translation with Conditional Adversarial Networks and wondered on formulas. For example, the objective of the CGAN is:
,
where x - observed image,...
0
votes
1
answer
55
views
References of deep learning and ai for dsp researchers [closed]
Are there excellent references for machine learning, deep learning and ai for DSP researchers?
1
vote
0
answers
20
views
Backpropagation in a Network [closed]
Hi does anyone know how to solve this. Im really struggling to figuring this one out.
I am unclear of how the backpropagation part would work in this network and how to calculate it for each weight. ...
0
votes
0
answers
90
views
Audio RMS normalization prior to a DNN classification
I want to normalize my data prior to a deep neural network model (DNN). It was recommended to me to use real mean square (RMS) normalization for audio, though I am not sure this is the best for a DNN. ...
5
votes
1
answer
389
views
how to handle different durations of audio data?
I am new to signal preprocessing, I read about mel_spectrograms, MFCC's. Now I want to apply it and use the CNN model, But the data which I have for practice is having audio of different durations, ...
0
votes
0
answers
41
views
multi-frame image restoration
Suppose we have a sequence of still images each of which has been contaminated by some particles(ex, dust/sand/smoke) making the images very poor in certain areas.
What approach would be best to teach ...
5
votes
2
answers
1k
views
Classic Signal Processing vs Deep Learning / Machine Learning (DNN / ML) Based Signal Processing
Are classic signal processing/statistics based approaches to optimum detection/estimation still relevant/important compared to ML based approaches using DL?
There was a time when speech processing was ...
1
vote
1
answer
48
views
Why not use synthetic datasets for training machine vision (deep learning) algorithms?
I am studying some examples of how to perform 3D instance segmentation in indoor scenes, and I have noticed many of the available datasets are from real environments. I was wondering with the ...
1
vote
0
answers
32
views
what should be a good bibliography for deep learning in 2020
What should be a good bibliography for having a good overview of deep learning (on image/signal processing) in 2020 ?
0
votes
0
answers
93
views
Remove noise from VGA image
I have 2 color images generated from same X-ray machines, but one of the image is obtained using VGA cable. Therefore the RGB intensities differ in the 2 images. I am using Object detection to detect ...
0
votes
0
answers
143
views
PCA with CNN Tensorflow
I need to improve my model of Convolutional Neural Network (CNN). The goal is to recognize facial expression.
I've been using some strategies like dropout for regularization and Adam optimazer, but i ...
2
votes
1
answer
62
views
Is it useful to apply edge detection filter as a preprocessing step before applying CNN?
Background: my future boss would like me to apply a number of low level filters to industrial images before applying machine learning methods on them.
From my knowledge this doesn't make any sense as ...
3
votes
2
answers
164
views
How to Design a Model based on Convolutional Neural Network (CNN) which Supports Arbitrary Input Size in Training and Production
I'm doing a research about personality identification based on their signature using CNN method, however the learning feature for the personality traits have a different input size. I understand that ...
0
votes
1
answer
72
views
Deep Learning: Classification vs. Convolution for Signal Restoration
Assume we have vector $X = [x_1, x_2, x_3, x_4 ,..... x_N], ∈ -1,1$. Therefore the value of $x$ is either 1 or -1. The vector $X$ is convoluted with random generated vector $Y$ whose length is the ...
0
votes
0
answers
33
views
Audio in Image,Graph or WaveForm Representation
Our task is to feed the audio data into the deep learning tensor flow model in the form of image representation(or graphical,waveform). Question is what is the best way of representing audio in image ...
0
votes
0
answers
1k
views
Understanding liftering as the final step in MFCCs features extraction
In the book here, they apply liftering, as a final step of MFCCs features extraction, to isolate the system component by multiplying the whole cepstrum by a rectangular window centred on lower ...
1
vote
0
answers
45
views
Adversarial training: deep learning book
In the Deep Learning book of Ian Goodfellow, p. 261 it is shown how to build an "adversarial example" by adding to an image $x$ another image $x_{adversarial}$ build as epsilon times and image (same ...