Questions tagged [deep-learning]
The deep-learning tag has no usage guidance.
45
questions
0
votes
0answers
16 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 ...
0
votes
2answers
86 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 ...
0
votes
0answers
18 views
Pretrained networks with Adam optimizer?
I have tried different pretrained networks with Adam optimizer, and obtained high performance. However, when I tried it with Alex network, the performance was poor. Could you please help me ...
0
votes
1answer
18 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
0answers
26 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
0answers
34 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
0answers
21 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 ...
0
votes
0answers
9 views
How to implement a single shot object detector with only āoneā anchor box per feature-map cell
I am newbie to SSD model, I have some images of products on a shelf , I trying to detecting that products using SSD with one anchor box per feature map, please help me out, how to prepare the data and ...
0
votes
0answers
16 views
How would one obtain 3D coordinates from 2D coordinates as well as the roll, pitch and yaw values of the observing camera?
I am trying to decipher the ParkNet DNN introduced by Nvidia. With no research paper released, this is proving quite a hassle. Right at the end of the blog post, it is mentioned that, using the roll ...
0
votes
0answers
18 views
Difference among motion vector, motion field and optical flow
I have started working on real-time recognition with deep learning and I read in many articles that optical flow can't work in real-time with deep neural networks, because of computational time.
I ...
1
vote
1answer
36 views
How to prepare different input size in CNN
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
1answer
51 views
Deep Learning: Classification vs. Convolution for Signal Restoration
Assume we have vector $X = [x_1, x_2, x_3, x_4 ,..... x_N], ā -1,1$. 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
0answers
29 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
0answers
226 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
0answers
32 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 ...
0
votes
0answers
38 views
Deep Learning based NDA Channel Estimation
I was wondering if it is possible to use Deep Learning to estimate the Channel Impulse Response for NDA synchronization?
I understand Deep Learning is not normally used for regression problems but I ...
0
votes
2answers
54 views
Could modulation/coding schemes be generated from an AI?
Warning: I'm a bit of a noob with respect to this entire field, but I took some classes on it (a few years ago) and found it fascinating.
Anyhow, as far as I understand it, modulation is the process ...
0
votes
1answer
28 views
Removing vocal but retaining all background ambient noises
I have one audio file containing human speeches, a lot of ambient noises like audience laughter, birds chirping, sounds of natures etc..
Now I want to separate it into two audio files where one ...
1
vote
1answer
63 views
Neural networks in system identification - What type of activation functions?
I made a free software for all operative systems, even Android. It's called Deeplearning2C. It can train a neural network and generate C code and MATLAB-code. C-code for embedded systems and MATLAB-...
0
votes
0answers
21 views
Targets for Deep Neural Network in acoustic model for speech recognition
I'm trying to come up to speed on the use of deep neural networks for speech recognition and I'm confused about what exactly are the targets for the DNN. I understand that the DNN tries to predict a ...
0
votes
0answers
35 views
convolutional deep Neural Networks for matrix
I have a basic question about using convolutional neural networks. It's not my field but I'd like to read and understand about it.
What I know that convolutional neural networks is used for image ...
0
votes
1answer
61 views
Which Machine or deep learning algorithm is appropriate of this issue?
Suppose I have $n$ features as $Y$ = ($y_1 , y_2 ...., y_n$), and a matrix of $J$ of dimension $M$x$N$, one feature of $Y$ is selected randomly to be convolved with one random column of $J$ resulting ...
1
vote
1answer
36 views
Are delta and double delta features needed when classifying with LSTM
I understand that the combination of MFCCs, deltas and double deltas is a good feature to be used with HMMs for keyword detection problems. HMMs are limited by Markov Property and this limitation is ...
1
vote
2answers
157 views
Augmentation for EEG signal classification using Deep Learning
Augmentation is a technique that we use in deep learning for expanding the training dataset. It includes different ways of modifying an image and adding it to the training dataset. My question is if ...
1
vote
1answer
192 views
How to express STFT and ISTFT as a 1d convolution and 1d deconvolution in tensorflow/keras
I'm trying to implement this paper in tensorflow and keras. At the end of section 3 it says.
...
2
votes
2answers
717 views
audio spectrogram normalization
I am performing language classification from audio signals using mel-spectrograms as my inputs for a ResNet. It works well as long as all of my audio data from different languages is from the same ...
0
votes
1answer
43 views
What does it mean for a Wavelet transform to commute with translations?
Referencing this article here https://arxiv.org/pdf/1203.1513.pdf
It states "A wavelet transform commutes with translations, and is therefore not translation invariant". Now I understand why it is a ...
1
vote
2answers
257 views
What fps can be considered as a hardline for real-time performance? Is there any academic paper that describes this?
I am trying to design a deep learning based inferencing solution for security applications. My deployed program achieves an FPS of 15fps for classification. Can it be considered real-time?
6
votes
3answers
2k views
Neural Networks and Complex Valued Inputs
[not sure if this or stats.stackexchange was the correct location for this post, so put it on both for now.]
I've seen some recent papers describing complex valued neural networks like this one: Deep ...
2
votes
1answer
145 views
Is deep learning the only way to detect humans in a picture?
I'm looking for a way to detect humans in a picture. For instance, regarding the picture below, I'd like to coarsely determine how many people are in the scene. I must be able to detect both standing ...
1
vote
1answer
78 views
In Convolutional Neural Nets, what do convolutions look like?
The early stages of the Convolutional Neural Networks are performing classical convolutions with a certain kernel size on the input image. Is is possible to express in common terms the type of ...
0
votes
1answer
52 views
Does the audio signal in the time domain change much after a RMS from one person to another?
I would like to train a deep neural network to perform lip syncing given an audio input like in this article.
I want to train my neural network only on Obama speeches like done in the article and ...
2
votes
1answer
295 views
RNN as posterior probability estimation in speech recognition with HTK
I'm new to speech recognition and deep learning and in a learning phase.
I'm trying to follow this paper to learn how to use RNN as posterior probability estimation in an HTK environment. The paper ...
2
votes
1answer
972 views
Training a CNN-HMM model
I am currently trying to train a CNN-HMM acoustic model for speech recognition.
The CNN model is able to detect a center monophone given a context window of x (limits has not been tested yet - but ...
0
votes
1answer
48 views
Deep learning model for phone recognition - issues with dimension the model
I seem to have some problems understandind how the model described in this paper has been designed
This is what is written about the model dimension..
...In these experiments we used one ...
1
vote
0answers
75 views
Pose-invariant face detection and recognition
I would like to detect faces and later apply recognition algorithms to surveillance videos. Ideally, the application should run in real-time (or near real-time) and transfer the data first to an ...
1
vote
0answers
2k views
Image preprocessing for facial detection->embedding->clustering pipeline
I am trying to implement an end to end pipeline for facial clustering so that it can group people with the same faces. This will be quote a long post as I know that this is a very broad topic, so I ...
1
vote
1answer
138 views
image reconstruction using a set of kernels
I try to be brief. For what I understood Convolutional Neural Network CNN for style-transfer extract/learn the main features of source Image. I think these features basically are Kernels (of different ...
-1
votes
1answer
453 views
Is image annotation a hard AI problem? [closed]
From Wikipedia "In the field of artificial intelligence, the most difficult problems are informally known as AI-complete or AI-hard, implying that the difficulty of these computational problems is ...
2
votes
3answers
3k views
Principal Component Analysis (PCA) on Convolutional Neural Network (CNN) Features
Please, I have a question regarding PCA and features which are extracted from a convolutional layer. link
if we have a test dataset , and we extract all conv features of all images at test dataset ...
4
votes
1answer
8k views
When is a network called end-to-end training?
In machine learning, we often see the expression "end-to-end" learning (or training). However, I do not know that it means. When is a network called end-to-end training? How to recognize a network is ...
4
votes
2answers
8k views
Can deep neural networks achieve real-time video analysis?
Recently, convolutional neural network based, deep architectures (DNN) such as AlexNet and VGGnet have been very successful in image classification challenges (e.g. ImageNet) and action recognition/...
59
votes
11answers
18k views
Is deep learning killing image processing/computer vision?
I'm looking forward to enroll in an MSc in Signal and Image processing, or maybe Computer Vision (I have not decided yet), and this question emerged.
My concern is, since deep learning doesn't need ...
0
votes
1answer
63 views
neural network for 3D pictures
I'm wondering if they are some state-of-art algorithms to apply the convolutional neural network approach to 3D pictures, eg. input is no longer a grid of pixels, but voxels. My objective is to ...
2
votes
1answer
275 views
Opinion about this aproach on Machine Learning
I have a question for you that maybe you could give me a clue.
I'm trying to make a CBIR (Content-Based Image Retrieval), so I query an image and I get the most similar, not classified within a ...
