Questions tagged [convolutional-neural-networks]
For questions about convolutional neural networks, also known as CNN or ConvNet.
992
questions
0
votes
0answers
12 views
what are the factors that make different Kernels in CNN? [duplicate]
what are the factors that affect the number of kernels and filters on CNN ? like one is 256 sometimes or 128 .. What does this change depend on? what is the difference between kernel and filter in the ...
0
votes
0answers
16 views
How to colorize images with Variational Autoencoder?
CONTEXT
I'm trying to colorize images with Variational Autoencoder. Input is 256x256 gray image. Output is 256x256x2 as I convert image to a LAB color space and then put gray channel as input and ...
0
votes
2answers
38 views
Are there any works that deal with 2D pose estimation in videos?
Since pose estimation is often a task where spatial-temporal context should be helpful in finding subsequent key points, I thought there should be many papers on it. However, I could not find any work ...
0
votes
0answers
16 views
How to prepare object detection annotation data from xml file to the form of grid cells? [closed]
I am implementing the YOLO object detection from scratch. I have my custom dataset for it which contains images and xml files. The xml files xmin, xmax, ymin, ymax and the class. From there I can't ...
0
votes
0answers
15 views
How to force/instruct CNN to learn specific features?
Let's say I have a CNN that classifies shirts. And let's say that it performs poorly on shirts that have horizontal stripes. How would I force network to put more emphasis on shirts with horizontal ...
0
votes
1answer
22 views
What is meant by "lateral connection" in the context of neural networks?
A class of CNN is popular due to the implementation of residual connections.
We can use both terms "residual connections" and "skip connections" interchangeably as they refer to ...
1
vote
2answers
253 views
Are these book example CNN results realistic?
I've been following a deep learning book and the current section I'm on is about convolutional neural networks. The author presents some code to create a basic CNN with about 1 million parameters, ...
2
votes
1answer
57 views
Can CNNs detect image similarity?
I have been running some experiments to see whether a CNN can detect whether two images are the same. However, I can't seem to make it work. I am wondering whether CNNs are not able to do what I am ...
0
votes
1answer
29 views
Is the phrase "Feature Pyramid Network" refer to CNN only?
"Feature Pyramid Network" is a network that is used for feature extraction. Since it is pyramid in shape, it might be called so.
Consider the following excerpts from two different sources
#1
...
0
votes
1answer
47 views
How many layers and neurons in a FFNN do I need to make it equivalent to a CNN?
I started to learn machine learning early, and I studied the convolutional neural network and its ability to understand images and how it helps to reduce the number of parameters that need to be tuned....
0
votes
0answers
18 views
Augmented an Image with other data when training CNN
In the typical RL/MDP framework, I have offline data of $(s,a,r,s')$ of expert Atari gameplay.
I'm looking to train a CNN to predict $r$ based on $(s, a)$.
The states are represented by a $4 \times 84 ...
0
votes
1answer
13 views
Why is training all layers at a time effective for a multi-layer autoencoder?
This training of all layers of a CNN simultaneously is standard practice today. It is found in every CNN (AlexNet (2012), VGG, Inception, GANs, etc) and even pre-CNN networks such as Le et al. 2012.
...
0
votes
0answers
18 views
Object Center-point detection/tracking without bounding box
The dataset is of microscopic cells. The data format is that it comes with annotations of the center point location of each cell.
Usually, the object detection/tracking dataset comes with a bounding ...
0
votes
0answers
18 views
Can I use a Mask R-CNN to detect a skin texture?
I'm trying to implement a solution in python to detect skin in an image.
I'm evaluating the Mask R-CNN model to create a mask on the skin (not on clothes). The problem is that every solution I have ...
0
votes
0answers
22 views
How do I apply non-max suppression for 2-classes problems?
I have basic knowledge about non-max suppression and I know how it works for multiple classes, but what if I want to get a prediction for two classification problems?
I give you an example. So I have ...
0
votes
1answer
52 views
Are the output dimensions of the first and second convolutional layer in YOLO paper correct?
I was reading the last version of the YOLO paper available in Arxiv, and I don't fully understand the output dimensions (I understand width and height, but not depth) of the first and second ...
1
vote
1answer
24 views
Is image machine translation done in two steps?
Suppose I have images of hand-written Japanese text. If I want to translate those images, would my ML algorithm be a 2-step model (for example, a CNN to convert the image into Japanese characters/...
0
votes
0answers
10 views
Including Object scale/dimension information in features generated by a CNN
I am working on a project where one of the tasks I need to do is to create embeddings for sketches. The sketches in question here are CAD Sketches. Being CAD sketches, the dimension information of the ...
0
votes
0answers
33 views
How to improve accuracy of CNN used for facial micro-expression analysis
From the paper (1) Facial expression analysis using CNN, the results using CNN show a 65% and 62% accuracy respectively, for emotion classification and state of mind identification.
Proposed Method:
...
0
votes
0answers
33 views
Predict placement of an object in 3D space
I am trying to find a way to train a model to predict the correct placement of entities like a tree, dog and cat in a natural 3D environment. Any help regarding how I could use textual data to learn ...
0
votes
1answer
21 views
Neural network for recognizing ship types based on location series
I am building a neural network for recognizing ship types based on a 1000-long series of location data (latitude-longitude, normalized to account for different km/longitude° metrics, so that vector ...
0
votes
0answers
15 views
In general, when are the normal, uniform and zero initializers used?
I came across a Conv2D layer in a fully convolutional network, which used a kernel_initializer='zero' for regression. Why is a ...
0
votes
1answer
32 views
Non-sliding kernels for location-aware processing in Convolutional Neural Networks
My understanding of how CNN operates in image detection is through the use of kernels that slide through the image to detect features (edges and so on). So a single kernel could potentially be ...
0
votes
0answers
21 views
Why batch normalization before upsampling is giving worse results?
I am training a model to generate images.
The model contains 5+5 layers:
...
2
votes
0answers
40 views
What is the stride information of an image referring here?
In convolutional neural networks, the convolution and pooling operations have a parameter known as stride, which decides the amount of jump the kernel needs to do on the input image. You can get more ...
1
vote
1answer
37 views
Are derived or computed inputs bad for CNNs?
I am building a CNN and am wondering if inputting derived or computed inputs are generally bad for the effectiveness of CNNs? Or just NNs in general?
By derived or computed values I mean data that is ...
0
votes
0answers
22 views
What loss function should be used for negative log likelihood labels
I am trying to build a ranking CNN model for document - query pairs using MS Marco dataset and python pytorch. My supervisor suggested to use the same CNN to extract feature vector for document and ...
0
votes
0answers
30 views
Why am I getting a very small number as CNN prediction?
I created a CNN using Tensorflow to identify pneumonia and sometimes it returns a very small number as a prediction. why is this happening?
I have attached the link for the dataset
Here I how I ...
1
vote
0answers
25 views
Does the Frechet Inception Distance (FID) consider color?
I was wondering if the Frechet inception distance
for two colored datasets would be the same than the FID calculated for the same datasets converted to grayscale.
I know that it depends on the feature ...
3
votes
1answer
39 views
In a Temporal Convolutional Network, how is the receptive field different from the input size?
I'm playing around with TCN's lately and I don't understand one thing. How is the receptive field different from the input size?
I think that the receptive field is the time window that TCN considers ...
0
votes
0answers
25 views
Orthogonalizing Convolutional Layers with the Cayley Transform
I'm reading this paper: "Orthogonalizing Convolutional Layers with the
Cayley Transform" regarding the orthogonalization of convolutional layers, i.e. enforcing learning of orthogonal ...
2
votes
1answer
29 views
Best practice for handling letterboxed images for non fully-convolutional deep learning networks?
I'm working on a depth estimation network. It has two outputs:
A relative depth map
A scalar for scaling the relative depth map into an absolute depth map. This second output uses dense layers so ...
0
votes
1answer
33 views
Is a Conv2DTranspose the same as a full convolution?
I am currently creating a GAN model from scratch (following this tutorial: https://machinelearningmastery.com/how-to-develop-a-generative-adversarial-network-for-an-mnist-handwritten-digits-from-...
2
votes
0answers
36 views
Decreasing number of neurons in CNN
the conventional way of creating a CNN is using increasing number of neurons:
...
1
vote
0answers
25 views
CNN: Difficulties understanding backward pass derivatives
I have really quite hard difficulties to understand what is actually going on in the backward pass of a CNN.
I am currently focusing on these references:
https://towardsdatascience.com/forward-and-...
0
votes
0answers
37 views
2D models on 3D tasks (convolutions): simple replace?
2D tasks enjoy a vast backing of successful models that can be reused.
For convolutions, can one simply replace 2D operations with 3D counterparts and inherit their benefits? Any 'extra steps' to ...
1
vote
1answer
46 views
What is the analytical formula for "Kaiming He" probability density function?
A probability density function is a real-valued function that roughly gives the density of probability at a particular value of a random variable.
For example, the probability density function of a ...
1
vote
1answer
56 views
Is there any paper that shows that multi-channel neural networks are universal approximators?
Lately, I have been reading a lot about the universal approximation theorem. I was surprised to find only theorems about "single-channel" standard networks (multi-layer perceptrons), where ...
1
vote
1answer
55 views
CNN Architectures for local features vs global context
Kaparthy in his blog post said
[this] hints at the kinds of architectures we’ll eventually explore. As an example - are very local features enough or do we need global context?
I'd like to gain ...
0
votes
1answer
14 views
Simple Image-based example for not utilising the variable-sized input handling capability of a Convolutional neural network
Convolutional neural networks are capable of handling inputs of varying sizes. It is one of the key benefits of convolutional neural networks. But I am unsure about the cases when we should not ...
0
votes
0answers
18 views
Improve generalization of phishing website detection with computer vision
I want to use computer vision to detect phishing websites. There has already been some study on this, which showed this is effective. Most phishing sites try to replicate well-known websites such as ...
1
vote
0answers
28 views
How to use K-means clustering to visualise learnt features of a CNN model?
Recently, I was going through the paper Intriguing Properties of Contrastive Losses. In the paper (section 3.2), the authors try to determine how well the SimCLR framework has allowed the ResNet50 ...
1
vote
0answers
43 views
Hand Landmark Detector Not Converging
I'm currently trying to train a custom model with TensorFlow to detect 17 landmarks/keypoints on each of 2 hands shown in an image (fingertips, first knuckles, bottom knuckles, wrist, and palm), for ...
1
vote
1answer
26 views
When is an object detection approach over a CNN approach appropriate?
I understand that CNNs are for image classification while object detection is for localization + classification of the objects detected. However, in particular, AI for chest radiographs, why is object ...
1
vote
1answer
35 views
Is there any recommended way to perform pooling in this context?
Suppose I have three batches of feature maps, each of size $180 \times 100 \times 100$. I want to concatenate all these feature maps channel-wise, and then resize them into a single feature map. The ...
2
votes
2answers
37 views
Improving validation losses and accuracy for 3D CNN
I have used a 3D CNN architecture, for detecting the presence of a particular promoter (MGMT), by using FLAIR brain scans. (64 slices per patient). The output is supposed to be binary (0/1).
I have ...
2
votes
1answer
109 views
How do I choose the hyper-parameters for a model to detect different guitar chords?
I need to build a hand detector that recognizes the chord played by a hand on a guitar.
I read this article Static Hand Gesture Recognition using Convolutional Neural Network with Data Augmentation ...
1
vote
1answer
29 views
What is meant by "spatial encoding" in the context of convolutional neural networks?
Consider the following excerpt from the abstract of the research paper titled Squeeze-and-Excitation networks by Jie Hu et al.
Convolutional neural networks are built upon the convolution operation, ...
0
votes
2answers
78 views
What do people refer to when they use the word 'dimensionality' in the context of convolutional layer?
In practical applications, we generally talk about three types of convolution layers: 1-dimensional convolution, 2-dimensional convolution, and 3-dimensional convolution. Most popular packages like ...
0
votes
1answer
32 views
When to use Multi-class CNN vs. one-class CNN
I'm building an object detection model with convolutional neural networks (CNN) and I started to wonder when should one use either multi-class CNN or a single-class CNN. That is, if I'm making e.g. a ...
